Updated on 2025/03/27

写真a

 
Ninomiya Takashi
 
Organization
Graduate School of Science and Engineering (Engineering) Major of Science and Engineering Applied Information Engineering Professor
Title
Professor
Contact information
メールアドレス
External link

Degree

  • Bachelor of Science ( The University of Tokyo )

  • Master of Science ( The University of Tokyo )

  • Ph.D. ( The University of Tokyo )

Research Interests

  • 自然言語処理

  • Computational Linguistics

  • Natural Language Processing

  • 計算言語学

Research Areas

  • Informatics / Intelligent informatics  / natural language processing

Education

  • The University of Tokyo   Graduate School of Science   Department of Information Science, Ph. D course

    1998.4 - 2001.3

      More details

    Country: Japan

    researchmap

  • The University of Tokyo   Graduate School of Science   Department of Information Science, Master course

    1996.4 - 1998.3

      More details

    Country: Japan

    researchmap

  • The University of Tokyo   Faculty of Science   Department of Information Science

    1993.10 - 1996.3

      More details

    Country: Japan

    researchmap

  • The University of Tokyo   Natural Science II

    1992.4 - 1993.9

      More details

Research History

  • Ehime University   Graduate School of Science and Engineering   Professor

    2017.4

      More details

  • Ehime University   Graduate School of Science and Engineering   Associate Professor

    2010.7 - 2017.3

      More details

  • The University of Tokyo   Information Technology Center   Lecturer

    2006 - 2010

      More details

  • Japan Science and Technology Agency   Research Associate

    2001 - 2006

      More details

  • Japan Society for the Promotion of Science (JSPS)

    1998 - 2001

      More details

Professional Memberships

▼display all

Committee Memberships

  • 言語処理学会   理事  

    2020.4 - 2024.3   

      More details

    Committee type:Academic society

    researchmap

  • アジア太平洋機械翻訳協会(AAMT)   理事  

    2018.8   

      More details

    Committee type:Academic society

    researchmap

  • IAMT   MT Summit XV 7th Workshop on Patent and Scientific Literature Translation (PSLT 2017) Program Committee  

    2017.9   

      More details

    Committee type:Academic society

    researchmap

  • 電子情報通信学会   和文論文誌D 編集委員  

    2016.6 - 2020.5   

      More details

    Committee type:Academic society

    researchmap

  • IAMT   MT Summit XV 6th Workshop on Patent and Scientific Literature Translation (PSLT 2015) Program Committee  

    2015.10   

      More details

    Committee type:Academic society

    researchmap

  • 情報処理学会 自然言語処理研究会   運営委員  

    2015.4 - 2019.3   

      More details

    Committee type:Academic society

    researchmap

  • AAMT/Japio 特許翻訳研究会   第3回特許情報シンポジウム 組織委員  

    2014.11   

      More details

    Committee type:Academic society

    researchmap

  • 情報処理学会・電子情報通信学会   第14回情報科学技術フォーラム(FIT 2015) 現地実行委員  

    2014.4 - 2015.9   

      More details

    Committee type:Academic society

    researchmap

  • 人工知能学会 人工知能基本問題研究会   現地幹事  

    2013.11   

      More details

    Committee type:Academic society

    researchmap

  • 言語処理学会   編集委員  

    2013.9 - 2015.9   

      More details

    Committee type:Academic society

    researchmap

  • IAMT   MT Summit XIV 5th Workshop on Patent Translation (PSLT 2013) Program Committee  

    2013.9   

      More details

    Committee type:Academic society

    researchmap

  • 情報処理学会 四国支部   委員  

    2013.4 - 2015.4   

      More details

    Committee type:Academic society

    researchmap

  • 人工知能学会   全国大会(第28回) プログラム委員現地運営担当  

    2013.4 - 2014.5   

      More details

    Committee type:Academic society

    researchmap

  • AAMT/Japio 特許翻訳研究会   第2回特許情報シンポジウム 組織委員  

    2012.11   

      More details

    Committee type:Academic society

    researchmap

  • IAMT   MT Summit XIII 4th Workshop on Patent Translation (PSLT 2011) Program Committee  

    2011.9   

      More details

    Committee type:Academic society

    researchmap

  • AAMT/Japio 特許翻訳研究会   第1回特許情報シンポジウム 組織委員  

    2010.10   

      More details

    Committee type:Academic society

    researchmap

  • 言語処理学会   評議員  

    2010.4 - 2014.3   

      More details

    Committee type:Academic society

    言語処理学会

    researchmap

  •   ANLP 16th annual meeting PC member (2009.10-2010.3)  

    2009.10 - 2010.3   

      More details

  • 言語処理学会   第16回年次大会プログラム委員  

    2009.10 - 2010.3   

      More details

    Committee type:Academic society

    言語処理学会

    researchmap

  • IAMT   MT Summit XII 3rd Workshop on Patent and Scientific Literature Translation (PSLT 2015) Program Committee  

    2009.8   

      More details

    Committee type:Academic society

    researchmap

  •   IPSJ 71st annual meeting WG member (2008.11)  

    2008.11   

      More details

  • 情報処理学会   第71回全国大会プログラム編成WG委員  

    2008.11   

      More details

    Committee type:Academic society

    researchmap

  • 言語処理学会   第15回年次大会プログラム委員  

    2008.10 - 2009.3   

      More details

    Committee type:Academic society

    言語処理学会

    researchmap

  •   ANLP 15th annual meeting PC member (2008.10-2009.3)  

    2008.10 - 2009.3   

      More details

  • 情報処理学会・電子情報通信学会   第7回情報科学技術フォーラム(FIT 2008) イベント企画「情報爆発時代の自然言語処理の新展開−大規模ウェブリソースは対話を賢くするか?−」 企画・開催担当  

    2008.9   

      More details

    Committee type:Academic society

    researchmap

  • AAMT/Japio 特許翻訳研究会   委員 (2008.4~)  

    2008.4   

      More details

    Committee type:Academic society

    researchmap

  •   AAMT/Japio Patent Translation Meeting member (2008.4~)  

    2008.4   

      More details

  • WWW2008   併設ワークショップNLPIX プログラム委員  

    2008.4   

      More details

  •   WWW2008 workshop NLPIX PC member (2008.4)  

    2008.4   

      More details

  • 情報処理学会・電子情報通信学会   FIT2008 E-1自然言語処理 担当  

    2007.9 - 2008.9   

      More details

    Committee type:Academic society

    researchmap

  •   FIT2008 E-1 NL PC member (2007.9~2008.9)  

    2007.9 - 2008.9   

      More details

  • 電子情報通信学会   ハンドブック/知識ベース委員会 編幹事  

    2007.7   

      More details

    Committee type:Academic society

    電子情報通信学会

    researchmap

  •   IEICE Handbook/Knowledge-base NL committie board (2007.7~)  

    2007.7   

      More details

  •   電子情報通信学会 ハンドブック/知識ベース委員会 編幹事 (2007.7~)  

    2007.7   

      More details

  •   Young Researcher's Association for NLP (YANS) board (2006.11~2007.9)  

    2006.11 - 2007.9   

      More details

  • NLP若手の会(YANS)   幹事  

    2006.11 - 2007.9   

      More details

  •   COLING-ACL 2006 parsing session chair (2006.8)  

    2006.8   

      More details

  • 情報処理学会 自然言語処理研究会   幹事  

    2006.4 - 2010.3   

      More details

    Committee type:Academic society

    researchmap

  •   IPSJ SIGNL board (2006~)  

    2006   

      More details

  •   IPSJ journal editorial board (2003.6~2007.5)  

    2003.6 - 2007.5   

      More details

  • 情報処理学会   論文誌編集委員  

    2003.6 - 2007.5   

      More details

    Committee type:Academic society

    情報処理学会

    researchmap

▼display all

Papers

  • English-to-Japanese Multimodal Machine Translation Based on Image-Text Matching of Lecture Videos Reviewed

    Ayu Teramen, Takumi Ohtsuka, Risa Kondo, Tomoyuki Kajiwara, Takashi Ninomiya

    Proceedings of the 3rd Workshop on Advances in Language and Vision Research (ALVR)   86 - 91   2024.8

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:Association for Computational Linguistics  

    DOI: 10.18653/v1/2024.alvr-1.7

    researchmap

  • Multi-Source Text Classification for Multilingual Sentence Encoder with Machine Translation Reviewed

    Reon Kajikawa, Keiichiro Yamada, Tomoyuki Kajiwara, Takashi Ninomiya

    Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)   226 - 232   2024.6

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:Association for Computational Linguistics  

    DOI: 10.18653/v1/2024.naacl-srw.24

    researchmap

  • Semi-automatic Construction of a Word Complexity Lexicon for Japanese Medical Terminology. Reviewed

    Soichiro Sugihara, Tomoyuki Kajiwara, Takashi Ninomiya, Shoko Wakamiya, Eiji Aramaki

    Proceedings of the 6th Clinical Natural Language Processing Workshop   329 - 333   2024.6

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    DOI: 10.18653/v1/2024.clinicalnlp-1.29

    researchmap

    Other Link: https://dblp.uni-trier.de/db/conf/acl-clinicalnlp/acl-clinicalnlp2024.html#SugiharaKNWA24

  • Japanese-to-English Multi-Level Complexity-Controllable MT: Test Data and Multi-Reference-Based Learning Reviewed

    Kazuki Tani, Akihiro Tamura, Tomoyuki Kajiwara, Takashi Ninomiya, Tsuneo Kato

    Journal of Natural Language Processing   31 ( 2 )   456 - 478   2024.6

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)   Publisher:Association for Natural Language Processing  

    DOI: 10.5715/jnlp.31.456

    researchmap

  • MATCHA: Parallel Corpus for Japanese Text Simplification Based on Professionally Simplified Articles Reviewed

    Rina Miyata, Hyuga Koretaka, Hiroki Yamauchi, Daiki Yanamoto, Tomoyuki Kajiwara, Takashi Ninomiya, Yasuhiro Nishiwaki

    Journal of Natural Language Processing   31 ( 2 )   590 - 609   2024.6

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)   Publisher:Association for Natural Language Processing  

    DOI: 10.5715/jnlp.31.590

    researchmap

  • Evaluation Dataset for Japanese Medical Text Simplification Reviewed

    Koki Horiguchi, Tomoyuki Kajiwara, Yuki Arase, Takashi Ninomiya

    Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)   219 - 225   2024.6

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:Association for Computational Linguistics  

    DOI: 10.18653/v1/2024.naacl-srw.23

    researchmap

  • Evaluating ChatGPT’s Ability to Generate Japanese Reviewed

    Sora Tarumoto, Koki Hatagaki, Rina Miyata, Tomoyuki Kajiwara, Takashi Ninomiya

    Journal of Natural Language Processing   31 ( 2 )   349 - 373   2024.6

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)   Publisher:Association for Natural Language Processing  

    DOI: 10.5715/jnlp.31.349

    researchmap

  • Utilizing Longer Context than Speech Bubbles in Automated Manga Translation Reviewed

    Hiroto Kaino, Soichiro Sugihara, Tomoyuki Kajiwara, Takashi Ninomiya, Joshua Tanner, Shonosuke Ishiwatari

    Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)   17337 - 17342   2024.5

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Transfer Fine-tuning for Quality Estimation of Text Simplification Reviewed

    Yuki Hironaka, Tomoyuki Kajiwara, Takashi Ninomiya

    Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)   16738 - 16744   2024.5

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Characterizing Chat-oriented Dialogue System via Style Transfer Reviewed

    Risa Kondo, Reon Kajikawa, Tomoyuki Kajiwara, Takashi Ninomiya

    65 ( 3 )   657 - 666   2024.3

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    DOI: 10.20729/00233247

    researchmap

  • Mitigating Domain Mismatch in Machine Translation via Paraphrasing Reviewed

    Hyuga Koretaka, Tomoyuki Kajiwara, Atsushi Fujita, Takashi Ninomiya

    Proceedings of the 10th Workshop on Asian Translation (WAT 2023)   29 - 40   2023.9

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Distractor Generation for Fill-in-the-Blank Exercises by Question Type Reviewed

    Nana Yoshimi, Tomoyuki Kajiwara, Satoru Uchida, Yuki Arase, Takashi Ninomiya

    Proceedings of the ACL 2023 Student Research Workshop (ACL 2023 SRW)   276 - 281   2023.7

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Multimodal Neural Machine Translation Using Synthetic Images Transformed by Latent Diffusion Model Reviewed

    Ryoya Yuasa, Akihiro Tamura, Tomoyuki Kajiwara, Takashi Ninomiya, Tsuneo Kato

    Proceedings of the ACL 2023 Student Research Workshop (ACL 2023 SRW)   76 - 82   2023.7

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Automated Orthodontic Diagnosis from a Summary of Medical Findings Reviewed

    Takumi Ohtsuka, Tomoyuki Kajiwara, Chihiro Tanikawa, Yuujin Shimizu, Hajime Nagahara, Takashi Ninomiya

    Proceedings of the 5th Clinical Natural Language Processing Workshop   156 - 160   2023.7

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Parallel Corpus Filtering for Japanese Text Simplification Reviewed

    Koki Hatagaki, Tomoyuki Kajiwara, Takashi Ninomiya

    Proceedings of the Workshop on Text Simplification, Accessibility, and Readability (TSAR 2022)   12 - 18   2022.12

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Comparing BERT-based Reward Functions for Deep Reinforcement Learning in Machine Translation. Reviewed

    Yuki Nakatani, Tomoyuki Kajiwara, Takashi Ninomiya

    WAT@COLING   37 - 43   2022

     More details

    Publishing type:Research paper (international conference proceedings)  

    researchmap

    Other Link: https://dblp.uni-trier.de/rec/conf/aclwat/2022

  • Unsupervised Quality Estimation via Multilingual Denoising Autoencoder Reviewed

    Nishihara Tetsuro, Iwamoto Yuji, Yoshinaka Masato, Kajiwara Tomoyuki, Arase Yuki, Ninomiya Takashi

    Journal of Natural Language Processing   29 ( 2 )   669 - 687   2022

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)   Publisher:The Association for Natural Language Processing  

    Supervised quality estimation methods require a corpus that manually annotates qualities of translation outputs. To avoid such costly annotation process, previous studies have proposed unsupervised quality estimation methods based on machine translation models trained on a large-scale parallel corpora. However, these methods are not applicable to low-resource or zero-resource language pairs. This study addresses this problem by utilising a pre-trained multilingual denoising autoencoder. Specifically, the proposed method constructs a machine translation model by fine-tuning the multilingual denoising autoencoder with parallel corpora. It then estimates the translation quality as a forced-decoding probability of a translation output given its source sentence. The pre-trained denoising autoencoder captures linguistic characteristics across languages, which allows our method to evaluate translation quality of low-resource and zero-resource language pairs. Evaluation results on the WMT20 quality estimation task confirm that the proposed method achieves the best unsupervised quality estimation performance for five language pairs under the black box settings. Detailed analysis shows that the proposed method also performs well on under the zero-shot setting.

    DOI: 10.5715/jnlp.29.669

    CiNii Research

    researchmap

  • Hie-BART: Abstractive Summarization by Hierarchical BART Reviewed

    Akiyama Kazuki, Tamura Akihiro, Ninomiya Takashi, Kajiwara Tomoyuki

    Journal of Natural Language Processing   29 ( 3 )   835 - 853   2022

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)   Publisher:The Association for Natural Language Processing  

    This paper proposes a new abstractive summarization model for documents, hierarchical BART (Hie-BART), which captures the hierarchical structures of documents (i.e., their sentence-word structures) in the BART model. Although the existing BART model has achieved state-of-the-art performance on document summarization tasks, it does not account for interactions between sentence-level and word-level information. In machine translation tasks, the performance of neural machine translation models can be improved with the incorporation of multi-granularity self-attention (MG-SA), which captures relationships between words and phrases. Inspired by previous work, the proposed Hie-BART model incorporates MG-SA into the encoder of the BART model for capturing sentence-word structures. As for the improvement of summarization performance by the proposed method, the evaluation using the CNN/Daily Mail dataset shows an improvement of 0.1 points on ROUGE-L.

    DOI: 10.5715/jnlp.29.835

    CiNii Research

    researchmap

  • Multi-Task Learning for Chemical Named Entity Recognition with Chemical Compound Paraphrasing Reviewed

    Watanabe Taiki, Tamura Akihiro, Ninomiya Takashi, Makino Takuya, Iwakura Tomoya

    Journal of Natural Language Processing   29 ( 2 )   294 - 313   2022

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)   Publisher:The Association for Natural Language Processing  

    We propose a method to improve named entity recognition (NER) for chemical compounds using multi-task learning by jointly training a chemical NER model and a chemical compound name paraphrase model. Our method enables the NER model to capture chemical compound paraphrases by sharing the parameters of NER and the character embeddings based on long short-term memories (LSTM) with the paraphrase model. Experimental results on BioCreative IV CHEMDNER show that our method learning paraphrase contributes to improved accuracy.

    DOI: 10.5715/jnlp.29.294

    CiNii Research

    researchmap

  • A Japanese Dataset for Subjective and Objective Sentiment Polarity Classification in Micro Blog Domain. Reviewed

    Haruya Suzuki, Yuto Miyauchi, Kazuki Akiyama, Tomoyuki Kajiwara, Takashi Ninomiya, Noriko Takemura, Yuta Nakashima, Hajime Nagahara

    LREC   7022 - 7028   2022

     More details

    Publishing type:Research paper (international conference proceedings)  

    researchmap

    Other Link: https://dblp.uni-trier.de/rec/conf/lrec/2022

  • A Benchmark Dataset for Multi-Level Complexity-Controllable Machine Translation. Reviewed

    Kazuki Tani, Ryoya Yuasa, Kazuki Takikawa, Akihiro Tamura, Tomoyuki Kajiwara, Takashi Ninomiya, Tsuneo Kato

    LREC   6744 - 6752   2022

     More details

    Publishing type:Research paper (international conference proceedings)  

    researchmap

    Other Link: https://dblp.uni-trier.de/rec/conf/lrec/2022

  • Controllable Text Simplification with Deep Reinforcement Learning. Reviewed

    Daiki Yanamoto, Tomoki Ikawa, Tomoyuki Kajiwara, Takashi Ninomiya, Satoru Uchida, Yuki Arase

    AACL/IJCNLP (2)   398 - 404   2022

     More details

    Publishing type:Research paper (international conference proceedings)  

    researchmap

    Other Link: https://dblp.uni-trier.de/rec/conf/ijcnlp/2022-2

  • Emotional Intensity Estimation based on Writer's Personality. Reviewed

    Haruya Suzuki, Sora Tarumoto, Tomoyuki Kajiwara, Takashi Ninomiya, Yuta Nakashima, Hajime Nagahara

    AACL/IJCNLP 2022 (Student Research Workshop)   1 - 7   2022

     More details

    Publishing type:Research paper (international conference proceedings)  

    researchmap

    Other Link: https://dblp.uni-trier.de/rec/conf/ijcnlp/2022-s

  • Adversarial Training on Disentangling Meaning and Language Representations for Unsupervised Quality Estimation. Reviewed

    Yuto Kuroda, Tomoyuki Kajiwara, Yuki Arase, Takashi Ninomiya

    COLING   5240 - 5245   2022

     More details

    Publishing type:Research paper (international conference proceedings)  

    researchmap

    Other Link: https://dblp.uni-trier.de/rec/conf/coling/2022

  • A Japanese Masked Language Model for Academic Domain. Reviewed

    Hiroki Yamauchi, Tomoyuki Kajiwara, Marie Katsurai, Ikki Ohmukai, Takashi Ninomiya

    SDP@COLING   152 - 157   2022

     More details

    Publishing type:Research paper (international conference proceedings)  

    researchmap

    Other Link: https://dblp.uni-trier.de/rec/conf/coling/2022sdp

  • Neural Text Generation with Artificial Negative Examples to Address Repeating and Dropping Errors Reviewed

    Keisuke Shirai, Kazuma Hashimoto, Akiko Eriguchi, Takashi Ninomiya, Shinsuke Mori

    Journal of Natural Language Processing   28 ( 3 )   751 - 777   2021.9

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:Association for Natural Language Processing  

    DOI: 10.5715/jnlp.28.751

    researchmap

  • Synchronous Syntactic Attention for Transformer Neural Machine Translation Reviewed

    Hiroyuki Deguchi, Akihiro Tamura, Takashi Ninomiya

    Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: Student Research Workshop   2021.8

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:Association for Computational Linguistics  

    DOI: 10.18653/v1/2021.acl-srw.36

    researchmap

  • Supervised Visual Attention for Multimodal Neural Machine Translation Reviewed

    28 ( 2 )   554 - 572   2021.6

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)   Publisher:Association for Natural Language Processing  

    DOI: 10.5715/jnlp.28.554

    researchmap

  • Hie-BART: Document Summarization with Hierarchical BART Reviewed

    Kazuki Akiyama, Akihiro Tamura, Takashi Ninomiya

    Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop   2021.6

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:Association for Computational Linguistics  

    DOI: 10.18653/v1/2021.naacl-srw.20

    researchmap

  • Bilingual Subword Segmentation for Neural Machine Translation Reviewed

    Hiroyuki Deguchi, Masao Utiyama, Akihiro Tamura, Takashi Ninomiya, Eiichiro Sumita

    Journal of Natural Language Processing   28 ( 2 )   632 - 650   2021.6

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)   Publisher:Association for Natural Language Processing  

    DOI: 10.5715/jnlp.28.632

    researchmap

  • Grammatical Error Correction via Supervised Attention in the Vicinity of Errors. Reviewed

    Hiromichi Ishii, Akihiro Tamura, Takashi Ninomiya

    Proceedings of the 35th Pacific Asia Conference on Language, Information and Computation(PACLIC)   227 - 234   2021

     More details

    Publishing type:Research paper (international conference proceedings)   Publisher:Association for Computational Lingustics  

    researchmap

    Other Link: https://dblp.uni-trier.de/rec/conf/paclic/2021

  • Transformer-based Approach for Predicting Chemical Compound Structures Reviewed

    Yutaro Omote, Kyoumoto Matsushita, Tomoya Iwakura, Akihiro Tamura, Takashi Ninomiya

    Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing (AACL-IJCNLP 2020)   154 - 162   2020.12

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:Association for Computational Linguistics  

    researchmap

    Other Link: https://dblp.uni-trier.de/rec/conf/ijcnlp/2020

  • Bilingual Subword Segmentation for Neural Machine Translation Reviewed

    Hiroyuki Deguchi, Masao Utiyama, Akihiro Tamura, Takashi Ninomiya, Eiichiro Sumita

    Proceedings of the 28th International Conference on Computational Linguistics (COLING 2020)   4287 - 4297   2020.12

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:International Committee on Computational Linguistics  

    DOI: 10.18653/v1/2020.coling-main.378

    researchmap

    Other Link: https://dblp.uni-trier.de/rec/conf/coling/2020

  • Supervised Visual Attention for Multimodal Neural Machine Translation Reviewed

    Tetsuro Nishihara, Akihiro Tamura, Takashi Ninomiya, Yutaro Omote, Hideki Nakayama

    Proceedings of the 28th International Conference on Computational Linguistics (COLING 2020)   4304 - 4314   2020.12

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:International Committee on Computational Linguistics  

    DOI: 10.18653/v1/2020.coling-main.380

    researchmap

  • 係り受け構造に基づくAttentionの制約を用いたTransformerニューラル機械翻訳 Reviewed

    出口 祥之, 田村 晃裕, 二宮 崇

    自然言語処理   27 ( 3 )   553 - 571   2020.9

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • 係り受け構造に基づく相対的位置表現を考慮したTransformer NMT Reviewed

    表 悠太郎, 田村 晃裕, 二宮 崇

    自然言語処理   27 ( 2 )   281 - 298   2020.6

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • A Visually-Grounded Parallel Corpus with Phrase-to-Region Linking Reviewed

    Hideki Nakayama, Akihiro Tamura, Takashi Ninomiya

    Proceedings of the 25th International Conference on Language Resources and Evaluation (LREC)   2020.5

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Multi-Task Learning for Chemical Named Entity Recognition with Chemical Compound Paraphrase Reviewed

    Taiki Watanabe, Akihiro Tamura, Takashi Ninomiya, Takuya Makino, Tomoya Iwakura

    Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP 2019)   6245 - 6250   2019.11

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Dependency-Based Self-Attention for Transformer NMT Reviewed

    Hiroyuki Deguchi, Akihiro Tamura, Takashi Ninomiya

    Proceedings of the International Conference Recent Advances in Natural Language Processing 2019 (RANLP 2019)   239 - 246   2019.9

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Dependency-Based Relative Positional Encoding for Transformer NMT Reviewed

    Yutaro Omote, Akihiro Tamura, Takashi Ninomiya

    Proceedings of the International Conference Recent Advances in Natural Language Processing 2019 (RANLP 2019)   854 - 861   2019.9

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Study on Condition-Based Maintenance of Track Circuit using the Mahalanobis Distance Reviewed

    Shida Hiroshi, Ninomiya Takashi, Takahashi Hiroshi

    IEEJ Transactions on Industry Applications   139 ( 6 )   588 - 596   2019.6

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)   Publisher:The Institute of Electrical Engineers of Japan  

    The performance ability of a track circuit is important for safety and reliability of railway operation. Therefore, maintenance of the track circuit is based on time-based maintenance (TBM). However, TBM has a problem in keeping excessive maintenance because it is a uniform method that does not consider the environment of individual equipment. In this study, we focus on condition-based maintenance, which monitors the state of individual equipment and maintains the equipment after any abnormal diagnosis of the equipment before a fault occurs. We expect to realize rational maintenance. Therefore, we propose that the Mahalanobis Distance can be used as a threshold value to show the appropriate time for maintenance. Furthermore, we show the possibility of decreasing the maintenance cost by approximately 20%.

    DOI: 10.1541/ieejias.139.588

    CiNii Books

    CiNii Research

    researchmap

    Other Link: http://id.ndl.go.jp/bib/029781066

  • Multimodal Neural Machine Translation Using CNN and Transformer Encoder Reviewed

    Hiroki Takushima, Akihiro Tamura, Takashi Ninomiya, Hideki Nakayam

    Proceedings of the 20th International Conference on Computational Linguistics and Intelligent Text Processing (CICLing)   2019.4

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:EasyChair  

    Multimodal machine translation uses images related to source language sentences as inputs to improve translation quality. Previous multimodal Neural Machine Translation (NMT) models, which incorporate visual features of each image region into an encoder for source language sentences or an attention mechanism between an encoder and a decoder, cannot catch the relation between visual features from each image region. This paper proposes a new multimodal NMT model, which encodes an input image using a Convolutional Neural Network (CNN) and a Transformer encoder. In particular, the proposed image encoder first extracts visual features from each image region using a CNN, and then encodes an input image on the basis of the extracted visual features using a Transformer encoder, where the relation between visual features from each image region are captured by a self-attention mechanism of the Transformer encoder. The experiments on the English-German translation task using the Multi30k data set show that the proposed model achieves 0.96 BLEU points improvement against a baseline Transformer NMT model without image inputs and 0.47 BLEU points improvement against a baseline multimodal Transformer NMT model without a Transformer encoder for images.

    DOI: 10.29007/hxhn

    researchmap

  • CKYに基づく畳み込みアテンション構造を用いたニューラル機械翻訳 Reviewed

    渡邊 大貴, 田村 晃裕, 二宮 崇, Teguh Bharata Adji

    自然言語処理   26 ( 1 )   207 - 230   2019.3

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    researchmap

  • Short answer scoring using W-Bleu for regular assessment in vocational high school Reviewed

    Feddy Setio Pribadi, Teguh Bharata Adji, Adhistya Erna Permanasari, Takashi Ninomiya

    International Journal of Innovation and Learning   24 ( 4 )   437 - 447   2018.9

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    researchmap

  • Neural Machine Translation Incorporating Named Entity Reviewed

    Arata Ugawa, Akihiro Tamura, Takashi Ninomiya, Hiroya Takamura, Manabu Okumura

    Proceedings of the 27th International Conference on Computational Linguistics (COLING 2018)   3240 - 3250   2018.8

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Improvement in Domain-Specific Named Entity Recognition by Utilizing the Real-World Data Reviewed

    Suzushi Tomori, Takashi Ninomiya, Shinsuke Mori

    Journal of Natural Language Processing   24 ( 5 )   655 - 668   2017.12

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)  

    DOI: 10.5715/jnlp.24.655

    researchmap

  • CKY-based Convolutional Attention for Neural Machine Translation Reviewed

    Taiki Watanabe, Akihiro Tamura, Takashi Ninomiya

    Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers) (IJCNLP 2017 short)   2   1 - 6   2017.11

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Improvement in Domain Specific Word Segmentation by Symbol Grounding

    Suzushi Tomori, Hirotaka Kameko, Takashi Ninomiya, Shinsuke Mori, Yoshimasa Tsuruoka

    Journal of Natural Language Processing   24 ( 3 )   447 - 461   2017.6

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)   Publisher:言語処理学会  

    <p>We propose a novel framework for improving a word segmenter using information acquired from symbol grounding. The framework uses a dataset consisting of pairs of non-textual information and a commentary. We generate a pseudo-stochastically segmented corpus from the commentaries, and then build a neural network to predict relationships between non-textual information and the words. We generate a domain specific term dictionary by using the neural network for word segmenter. We applied our method to game records of Japanese chess with commentaries. The experimental results show that the accuracy of a word segmenter can be improved by incorporating the generated dictionary. </p>

    DOI: 10.5715/jnlp.24.447

    CiNii Books

    researchmap

  • Domain Specific Named Entity Recognition Referring to the Real World by Deep Neural Networks Reviewed

    Suzushi Tomori, Takashi Ninomiya, Shinsuke Mori

    Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) (ACL 2016 short)   236 - 242   2016

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Resampling Approach for Instance-based Domain Adaptation from Patent Domain to Newspaper Domain in Statistical Machine Translation Reviewed

    Keisuke Noguchi, Takashi Ninomiya

    Proceedings of the 6th Workshop on Patent and Scientific Literature Translation (PSLT6)   81 - 88   2015

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Acquiring distributed representations for verb-object pairs by using word2vec Reviewed

    Miki Iwai, Takashi Ninomiya, Kyo Kageura

    Proceedings of the 29th Pacific Asia Conference on Language, Information and Computation: Posters (PACLIC 2015 Poster)   328 - 336   2015

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Deep Learning for Large-Scale Sentiment Analysis Using Distributed Representations Reviewed

    Kazuhei Katoh, Takashi Ninomiya

    Proceedings of the 9th International Conference on Advances in Semantic Processing (SEMAPRO 2015)   92 - 96   2015

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Personalized Reading Support for Second-Language Web Documents Reviewed

    Yo Ehara, Nobuyuki Shimizu, Takashi Ninomiya, Hiroshi Nakagawa

    ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY   4 ( 2 )   31:1 - 31:19   2013.3

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:ASSOC COMPUTING MACHINERY  

    A novel intelligent interface eases the browsing of Web documents written in the second languages of users. It automatically predicts words unfamiliar to the user by a collective intelligence method and glosses them with their meaning in advance. If the prediction succeeds, the user does not need to consult a dictionary; even if it fails, the user can correct the prediction. The correction data are collected and used to improve the accuracy of further predictions. The prediction is personalized in that every user's language ability is estimated by a state-of-the-art language testing model, which is trained in a practical response time with only a small sacrifice of prediction accuracy. The system was evaluated in terms of prediction accuracy and reading simulation. The reading simulation results show that this system can reduce the number of clicks for most readers with insufficient vocabulary to read documents and can significantly reduce the remaining number of unfamiliar words after the prediction and glossing for all users.

    DOI: 10.1145/2438653.2438666

    Web of Science

    researchmap

  • Efficient Online Feature Selection based on l1-Regularized Logistic Regression Reviewed

    Kengo Ooi, Takashi Ninomiya

    Proceedings of the 5th International Conference on Agents and Artificial Intelligence (ICAART 2013)   2   277 - 282   2013

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Improving Efficiency of Online Grafting by Simultaneously Testing Multiple Features Reviewed

    Kengo OOI, Takashi NINOMIYA

    DBSJ Journal   11 ( 3 )   15 - 20   2013

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)   Publisher:日本データベース学会  

    CiNii Books

    researchmap

  • Deterministic shift-reduce parsing for unification-based grammars Reviewed

    Takashi Ninomiya, Takuya Matsuzaki, Nobuyuki Shimizu, Hiroshi Nakagawa

    NATURAL LANGUAGE ENGINEERING   17 ( 3 )   331 - 365   2011.7

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:CAMBRIDGE UNIV PRESS  

    Many parsing techniques assume the use of a packed parse forest to enable efficient and accurate parsing. However, they suffer from an inherent problem that derives from the restriction of locality in the packed parse forest. Deterministic parsing is one solution that can achieve simple and fast parsing without the mechanisms of the packed parse forest by accurately choosing search paths. We propose new deterministic shift-reduce parsing and its variants for unification-based grammars. Deterministic parsing cannot simply be applied to unification-based grammar parsing, which often fails because of its hard constraints. Therefore, this is developed by using default unification, which almost always succeeds in unification by overwriting inconsistent constraints in grammars.

    DOI: 10.1017/S1351324910000240

    Web of Science

    researchmap

  • An Efficient and Exact Solution of Passive-Aggressive Algorithm for Multiclass Classification Problems Reviewed

    Shin MATSUSHIMA, Nobuyuki SHIMIZU, Kazuhiro YOSHIDA, Takashi NINOMIYA, Hiroshi NAKAGAWA

    The IEICE transactions on information and systems (Japanese)   J93-D ( 6 )   724 - 732   2010.6

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)   Publisher:The Institute of Electronics, Information and Communication Engineers  

    多くの機械学習ではデータ全体に対して一つの最適な関数を求めるため,大量のデータに対して学習を行う際に計算コストの面から困難が生じる場合があるが,逐次学習法は,データを一つずつ受け取りながら逐次的に識別関数を学習していく手法であり,低い計算コストで学習可能である.Passive-Aggressiveアルゴリズムは代表的な逐次学習法による学習アルゴリズムであるが,多クラス識別問題においては,厳密なPassive-Aggressiveアルゴリズムの枠組みから外れた近似解法が用いられてきた.本論文では,本来のPassive-Aggressiveアルゴリズムの厳密解をサポートクラスという概念を用いて導出し,識別関数の更新を効率的に行うための定理の証明を与えるとともにこれらに基づくアルゴリズムを提案する.この手法に対する文書分類や手書き文字認識の実験を行い,既存のPassive-Aggressiveアルゴリズムより精度が高く,SVMに比べ同程度の精度をより高速に実現することを確認した.

    CiNii Books

    researchmap

  • An Empirical Study of PA Algorithm Using Unlabeled Data Reviewed

    Shin MATSUSHIMA, Issei SATO, Takashi NINOMIYA, Hiroshi NAKAGAWA

    DBSJ Journal   9 ( 1 )   82 - 87   2010.6

     More details

    Language:Japanese   Publishing type:Research paper (scientific journal)   Publisher:日本データベース学会  

    CiNii Books

    researchmap

  • Exact Passive-Aggressive Algorithm for Multiclass Classification Using Support Class Reviewed

    Shin Matsushima, Nobuyuki Shimizu, Kazuhiro Yoshida, Takashi Ninomiya, Hiroshi Nakagawa

    Proceedings of the 2010 SIAM International Conference on Data Mining (SDM10)   303 - 314   2010

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Personalized Reading Support for Second-Language Web Documents by Collective Intelligence Reviewed

    Yo Ehara, Nobuyuki Shimizu, Takashi Ninomiya, Hiroshi Nakagawa

    IUI 2010   51 - 60   2010

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:ASSOC COMPUTING MACHINERY  

    Novel intelligent interface eases the browsing of Web documents written in the second languages of users. It automatically predicts words unfamiliar to the user by collective intelligence and glosses them with their meaning in advance. If the prediction succeeds, the user does not need to consult a dictionary; even if it fails, the user can correct the prediction. The correction data are collected and used to improve the accuracy of further predictions. The prediction is personalized in that every user&apos;s language ability is estimated by a state-of-the-art language testing model, which is trained in a practical response time with only a small sacrifice of prediction accuracy. Evaluation results for the system in terms of prediction accuracy are encouraging.

    DOI: 10.1145/1719970.1719978

    Web of Science

    researchmap

  • Deterministic shift-reduce parsing for unification-based grammars by using default unification Reviewed

    Takashi Ninomiya, Takuya Matsuzaki, Nobuyuki Shimizu, Hiroshi Nakagawa

    Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics (EACL-09)   603 - 611   2009

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Fast and scalable HPSG parsing Reviewed

    Takashi Ninomiya, Yoshimasa Tsuruoka, Yusuke Miyao, Kenjiro Taura, Jun’ichi Tsujii

    Traitement Automatique des Langues (TAL)   46 ( 2 )   91 - 114   2007

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    researchmap

  • A log-linear model with an n-gram reference distribution for accurate HPSG parsing Reviewed

    Takashi Ninomiya, Takuya Matsuzaki, Yusuke Miyao, Jun’ichi Tsujii

    Proceedings of the 10th International Conference on Parsing Technologies (IWPT 2007)   60 - 68   2007

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Extremely Lexicalized Models for Accurate and Fast HPSG Parsing Reviewed

    Takashi Ninomiya, Takuya Matsuzaki, Yoshimasa Tsuruoka, Yusuke Miyao, Jun’ichi Tsujii

    Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing (EMNLP 2006)   155 - 163   2006

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Semantic Retrieval for the Accurate Identification of Relational Concepts in Massive Textbases Reviewed

    Yusuke Miyao, Tomoko Ohta, Katsuya Masuda, Yoshimasa Tsuruoka, Kazuhiro Yoshida, Takashi Ninomiya, Jun'ichi Tsujii

    COLING/ACL 2006, VOLS 1 AND 2, PROCEEDINGS OF THE CONFERENCE   1017 - 1024   2006

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:ASSOC COMPUTATIONAL LINGUISTICS-ACL  

    This paper introduces a novel framework for the accurate retrieval of relational concepts from huge texts. Prior to retrieval, all sentences are annotated with predicate argument structures and ontological identifiers by applying a deep parser and a term recognizer. During the run time, user requests are converted into queries of region algebra on these annotations. Structural matching with pre-computed semantic annotations establishes the accurate and efficient retrieval of relational concepts. This framework was applied to a text retrieval system for MEDLINE. Experiments on the retrieval of biomedical correlations revealed that the cost is sufficiently small for real-time applications and that the retrieval precision is significantly improved.

    Web of Science

    researchmap

  • Trimming CFG Parse Trees for Sentence Compression Using Machine Learning Approaches Reviewed

    Yuya Unno, Takashi Ninomiya, Yusuke Miyao, Jun’ichi Tsujii

    Proceedings of the COLING/ACL 2006 Main Conference Poster Sessions (COLING/ACL 2006 poster)   850 - 857   2006

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • An intelligent search engine and GUI-based efficient MEDLINE search tool based on deep syntactic parsing Reviewed

    Tomoko Ohta, Yusuke Miyao, Takashi Ninomiya, Yoshimasa Tsuruoka, Akane Yakushiji, Katsuya Masuda, Jumpei Takeuchi, Kazuhiro Yoshida, Tadayoshi Hara, Jin-Dong Kim, Yuka Tateisi, Jun’ichi Tsujii

    Proceedings of the COLING/ACL 2006 Interactive Presentation Sessions   17 - 20   2006

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Corpus-oriented grammar development for acquiring a head-driven phrase structure grammar from the Penn Treebank Reviewed

    Y Miyao, T Ninomiya, J Tsujii

    NATURAL LANGUAGE PROCESSING - IJCNLP 2004   3248   684 - 693   2005

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:SPRINGER-VERLAG BERLIN  

    This paper describes a method of semi-automatically acquiring an English HPSG grammar from the Penn Treebank. First, heuristic rules are employed to annotate the treebank with partially-specified derivation trees of HPSG. Lexical entries are automatically extracted from the annotated corpus by inversely applying HPSG schemata to partially-specified derivation trees. Predefined HPSG schemata assure the acquired lexicon to conform to the theoretical formulation of HPSG. Experimental results revealed that this approach enabled us to develop an HPSG grammar with significant robustness at small cost.

    Web of Science

    researchmap

  • A persistent feature-object database for intelligent text archive systems Reviewed

    T Ninomiya, J Tsujii, Y Miyao

    NATURAL LANGUAGE PROCESSING - IJCNLP 2004   3248   197 - 205   2005

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:SPRINGER-VERLAG BERLIN  

    This paper describes an intelligent text archive system in which typed feature structures are embedded. The aim of the system is to associate feature structures with regions in text, to make indexes for efficient retrieval, to allow users to specify both structure and proximity, and to enable inference on typed feature structures embedded in text. We propose a persistent mechanism for storing typed feature structures and the architecture of the text archive system.

    Web of Science

    researchmap

  • Efficacy of Beam Thresholding, Unification Filtering and Hybrid Parsing in Probabilistic HPSG Parsing Reviewed

    Takashi Ninomiya, Yoshimasa Tsuruoka, Yusuke Miyao, Jun’ichi Tsujii

    Proceedings of the Ninth International Workshop on Parsing Technologies (IWPT 2005)   103 - 114   2005

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Probabilistic modeling of argument structures including non-local dependencies Reviewed

    Yusuke Miyao, Takashi Ninomiya, Jun’ichi Tsujii

    Proceedings of the International Conference Recent Advances in Natural Language Processing 2003 (RANLP 2003)   285 - 291   2003

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • A Robust Retrieval Engine for Proximal and Structural Search Reviewed

    Katsuya Masuda, Takashi Ninomiya, Yusuke Miyao, Tomoko Ohta, Jun’ichi Tsujii

    Companion Volume of the Proceedings of HLT-NAACL 2003 - Short Papers (NAACL 2003 short)   58 - 60   2003

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Lexicalized Grammar Acquisition Reviewed

    Yusuke Miyao, Takashi Ninomiya, Jun’ichi Tsujii

    10th Conference of the European Chapter of the Association for Computational Linguistics Conference Companion (EACL 2003 short)   127 - 130   2003

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Action Vectors for Interpreting Route Descriptions Reviewed

    Junko Araki, Takashi Ninomiya, Takaki Makino, Jun’ichi Tsujii

    Proceedings of the AAAI-02 Workshop on Spatial and Temporal Reasoning   2002

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Lenient Default Unification for Robust Processing within Unification Based Grammar Formalisms Reviewed

    Takashi NINOMIYA, Yusuke MIYAO, Jun’ichi TSUJII

    Proceedings of the 19th International Conference on Computational Linguistics (COLING 2002)   744 - 750   2002

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Two perspective systems using a route as a reference object Reviewed

    J Araki, T Ninomiya, T Makino, J Tsujii

    6TH WORLD MULTICONFERENCE ON SYSTEMICS, CYBERNETICS AND INFORMATICS, VOL XIII, PROCEEDINGS   1 - 4   2002

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:INT INST INFORMATICS & SYSTEMICS  

    This paper discusses the spatial configuration between objects and a route which an agent follows according to instructions in a navigation task. We claim that a route can be regarded as a reference object and thereby two types of perspective system are defined; the route-centered perspective system and the position-centered perspective system. The route-centered perspective system is presented to partition a space by regarding a route as a boundary line. The position-centered perspective system is introduced to determine the spatial configuration between objects and the positions on the route. These perspective systems can explain tile human mental mechanism of the dialogue.

    Web of Science

    researchmap

  • An Indexing Scheme for Typed Feature Structures Reviewed

    Takashi NINOMIYA, Takaki MAKINO, Jun’ichi TSUJII

    Proceedings of the 19th International Conference on Computational Linguistics (COLING 2002)   1248 - 1252   2002

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Parallel Parsing and Robust Processing within Unification Based Grammar Formalism Reviewed

    Takashi Ninomiya

    Ph.D Thesis, Department of Information Science, Graduate School of Science, The University of Tokyo   2001.3

     More details

    Language:English   Publishing type:Doctoral thesis  

    researchmap

  • An Agent-based Parallel HPSG Parser for Shared-memory Parallel Machines Reviewed

    Takashi Ninomiya, Kentaro Torisawa, Jun’ichi Tsujii

    Journal of Natural Language Processing   8 ( 1 )   21 - 47   2001.1

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:言語処理学会  

    We describe an agent-based parallel HPSG parser that operates on shared-memory parallel machines. It efficiently parses real-world corpora by using a wide-coverage HPSG grammar. The efficiency is due to the use of a parallel parsing algorithm and the efficient treatment of feature structures. The parsing algorithm is based on the CKY algorithm, in which resolving constraints between a mother and her daughters is regarded as an atomic operation. The CKY algorithm features data distribution and granularity of parallelism. The keys to the efficient treatment of feature structures are i) transferring them through shared-memory, ii) copying them on demand, and iii) writing/reading them simultaneously onto/from memory. Being parallel, our parser is more efficient than sequential parsers. The average parsing time per sentence for the EDR Japanese corpus was 78 msec and its speed-up reaches 13.2 when 50 processors were used.

    DOI: 10.5715/jnlp.8.21

    CiNii Books

    researchmap

  • EFFICIENT FB-LTAG PARSER AND ITS PARALLELIZATION Reviewed

    MINORU YOSHIDA, TAKASHI NINOMIYA, KENTARO TORISAWA, TAKAKI MAKINO, JUN’ICHI TSUJII

    Proceedings of the conference Pacific Association for Computational Linguistics ’99 (PACLING ’99)   90 - 103   1999

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Parallel HPSG Parser Reviewed

    Takashi Ninomiya

    Master Thesis, Department of Information Science, Graduate School of Science, The University of Tokyo   1998.3

     More details

    Language:English   Publishing type:Master’s thesis  

    researchmap

  • An Efficient Parallel Substrate for Typed Feature Structures on Shared Memory Parallel Machines Reviewed

    NINOMIYA Takashi, TORISAWA Kentaro, TSUJII Jun’ichi

    Proceedings of the 17th International Conference on Computational Linguistics and the 36th Annual Meeting of the Association for Computational Linguistics (COLING-ACL ’98)   968 - 974   1998

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • A Parallel CKY Parsing Algorithm on Large-Scale Distributed-Memory Parallel Machines Reviewed

    NINOMIYA Takashi, TORISAWA Kentaro, TAURA Kenjiro, TSUJII Jun’ichi

    Proceedings of the conference Pacific Association for Computational Linguistics ’97 (PACLING ’97)   223 - 231   1997

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • 並列オブジェクト指向言語ABCL/fによる大規模並列計算機上のスケーラブルなCKYパーザー Reviewed

    二宮 崇, 田浦 健次朗, 鳥澤 健太郎, 辻井 潤一

    日本ソフトウェア科学会 オブジェクト指向計算ワークショップ (WOOC)   1997

     More details

    Language:Japanese   Publishing type:Research paper (conference, symposium, etc.)  

    researchmap

  • Lexical Preference Acquisition Based on Probabilistic Horn Constraint System (PHoCS) Reviewed

    Takashi Ninomiya

    Senior Thesis, Department of Information Science, Faculty of Science, The University of Tokyo   1996.3

     More details

    Language:English   Publishing type:Thesis (other)  

    researchmap

▼display all

Books

  • 電気工学ハンドブック (第7版)

    二宮 崇( Role: Contributor34編2章自然言語処理)

    オーム社  2013 

     More details

    Total pages:9   Responsible for pages:1758-1766   Language:Japanese   Book type:Dictionary, encyclopedia

    researchmap

  • Trends in Parsing Technology: Dependency Parsing, Domain Adaptation, and Deep Parsing

    Takashi Ninomiya, Takuya Matsuzaki, Yusuke Miyao, Yoshimasa Tsuruoka, Jun'ichi Tsujii( Role: Joint authorHPSG Parsing with a Supertagger)

    Springer-Verlag  2010 

     More details

    Total pages:14   Responsible for pages:243-256   Language:English   Book type:Scholarly book

    researchmap

  • 言語処理学事典

    二宮 崇( Role: Contributor2.3.2. 単一化文法, 2.4.4. 深い構文解析, 2.4.7. 文法獲得)

    共立出版  2009 

     More details

    Total pages:6   Responsible for pages:158-159, 176-177, 182-183   Language:Japanese   Book type:Dictionary, encyclopedia

    researchmap

MISC

  • ChatGPT4oを用いた要件定義の工程支援とその効果に関する考察

    新山 剛司, 阿萬 裕久, 二宮 崇

    ソフトウェアエンジニアリングシンポジウム2024論文集   2024   117 - 122   2024.9

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • Improving Japanese Sentiment Analysis with Text Normalization

    近藤里咲, 寺面杏優, 梶川怜恩, 堀口航輝, 梶原智之, 梶原智之, 二宮崇, 早志英朗, 中島悠太, 長原一

    ( 4Xin2-12 )   1 - 4   2024.5

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    J-GLOBAL

    researchmap

  • 日本語医療テキスト平易化の訓練用データセットの構築

    堀口 航輝, 梶原 智之, 二宮 崇, 若宮 翔子, 荒牧 英治

    人工知能学会 第38回全国大会論文集   ( 3S1-OS-7b-04 )   1 - 4   2024.5

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    DOI: 10.11517/pjsai.JSAI2024.0_3S1OS7b04

    researchmap

  • タスクの特性を考慮した教師なしパラレルコーパスフィルタリング

    畠垣光希, 樽本空宙, 梶原智之, 二宮崇

    人工知能学会 第38回全国大会論文集   ( 3Xin2-60 )   1 - 4   2024.5

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    DOI: 10.11517/pjsai.JSAI2024.0_3Xin260

    researchmap

  • Emotion Analysis with a Writer’s Multiple Posts

    ( 3Xin2-104 )   1 - 4   2024.5

     More details

  • 機械翻訳を用いた多言語文符号化器のマルチソース入力によるテキスト分類

    梶川怜恩, 山田啓一朗, 梶原智之, 二宮崇

    人工知能学会 第38回全国大会論文集   ( 4N3-GS-6-03 )   1 - 4   2024.5

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    DOI: 10.11517/pjsai.JSAI2024.0_4N3GS603

    researchmap

  • 言語横断類似度推定のための多言語文符号化器のドメイン適応

    山内洋輝, 梶原智之, 桂井麻里衣, 二宮崇

    言語処理学会 第30回年次大会発表論文集   1676 - 1680   2024.3

     More details

    Language:Japanese  

    J-GLOBAL

    researchmap

  • テキスト平易化の品質推定のための擬似訓練

    廣中 勇希, 梶原 智之, 二宮 崇

    言語処理学会 第30回年次大会発表論文集   2183 - 2187   2024.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • JParaCrawlからの大規模日本語言い換え辞書の構築

    近藤 里咲, 梶原 智之, 二宮 崇

    言語処理学会 第30回年次大会発表論文集   1736 - 1740   2024.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 大規模言語モデルによる日本語感情分析の性能評価

    近藤 里咲, 大塚 琢生, 梶原 智之, 二宮 崇, 早志 英朗, 中島 悠太, 長原 一

    情報処理学会 第86回全国大会講演論文集   859 - 860   2024.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 講演動画の画像言語マッチングに基づくマルチモーダル機械翻訳

    寺面 杏優, 大塚 琢生, 梶原 智之, 二宮 崇

    情報処理学会 第86回全国大会講演論文集   901 - 902   2024.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 日本語医療テキスト平易化の評価用データセットの構

    堀口 航輝, 梶原 智之, 荒瀬 由紀, 二宮 崇

    言語処理学会 第30回年次大会発表論文集   255 - 259   2024.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 文埋め込みに基づく日米の医薬品添付文書の文書マッチングの評価

    松田卓也, 黒田勇斗, 川上幸伸, 梶原智之, 二宮崇, 木村映善

    日本医療情報学会 第43回医療情報学連合大会   1610 - 1614   2023.11

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • Unsupervised Translation Quality Estimation Exploiting Synthetic Data and Pre-trained Multilingual Encoder

    Yuto Kuroda, Atsushi Fujita, Tomoyuki Kajiwara, Takashi Ninomiya

    arXiv   2311.05117   2023.11

     More details

    Language:English  

    researchmap

  • スタイル変換による雑談対話システムへのキャラクタ性の付与

    近藤 里咲, 梶川 怜恩, 梶原 智之, 二宮 崇

    第22回情報科学技術フォーラム (FIT 2023)   341 - 346   2023.9

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 漫画の機械翻訳における吹き出しよりも長い文脈情報の活用

    戒能 大翔, 梶原 智之, 二宮 崇, Tanner Joshua, 石渡 祥之佑

    第22回情報科学技術フォーラム (FIT 2023)   347 - 351   2023.9

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 系列変換タスクにおけるChatGPTの日本語生成能力の評価

    樽本 空宙, 畠垣 光希, 宮田 莉奈, 梶原 智之, 二宮 崇

    第22回情報科学技術フォーラム (FIT 2023)   329 - 336   2023.9

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • JParaBank: A Large-Scale Sentence Pairs of Japanese Paraphrase via Machine Translation

    TARUMOTO Sora, KORETAKA Hyuga, KAJIWARA Tomoyuki, NINOMIYA Takashi

    Proceedings of the Annual Conference of JSAI   JSAI2023   4Xin113 - 4Xin113   2023.6

     More details

    Language:Japanese   Publisher:The Japanese Society for Artificial Intelligence  

    To address the low-resource problem of machine learning tasks, including natural language processing, the effectiveness of data augmentation is well known. In recent natural language processing, data augmentation based on paraphrase generation has been used successfully in many applications. However, unlike English and Chinese, there is no large-scale corpus for training paraphrase generation models in Japanese, and thus data augmentation based on paraphrase generation is not available for Japanese. We release JParaBank, a large-scale Japanese paraphrase corpus of 21 million sentence pairs. Experimental results on the JGLUE benchmark show that data augmentation by paraphrase generation using JParaBank improves performance on many tasks.

    DOI: 10.11517/pjsai.jsai2023.0_4xin113

    CiNii Research

    researchmap

  • Trial of Sentence Alignment on Professionally Simplified Articles for Japanese Text Simplification

    KORETAKA Hyuga, YAMAUCHI Hiroki, YANAMOTO Daiki, MIYATA Rina, KAJIWARA Tomoyuki, NINOMIYA Takashi, NISHIWAKI Yasuhiro

    Proceedings of the Annual Conference of JSAI   JSAI2023   3Xin414 - 3Xin414   2023.6

     More details

    Language:Japanese   Publisher:The Japanese Society for Artificial Intelligence  

    Text simplification is the task that transforms complex text into simpler one while preserving its meaning. Previous parallel corpora in Japanese for this task are constructed from simple text written by students or crowd workers, and there are no parallel corpora written by experts. We are constructing a parallel corpus by manually aligning sentences in articles that have been simplified by experts. This paper reports on the analysis of a part of our corpus that has been constructed at present. The human evaluation showed that our corpus contains a variety of simplification operations and consists of simpler sentences than the existing ones.

    DOI: 10.11517/pjsai.jsai2023.0_3xin414

    CiNii Research

    researchmap

  • 言い換えによる機械翻訳のドメイン不適合の緩和

    惟高 日向, 梶原 智之, 藤田 篤, 二宮 崇

    言語処理学会 第29回年次大会 発表論文集   2517 - 2521   2023.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 疑似訓練データに基づく機械翻訳の教師なし品質推定

    黒田 勇斗, 藤田 篤, 梶原 智之, 二宮 崇

    言語処理学会 第29回年次大会 発表論文集   1283 - 1287   2023.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 問題タイプを考慮した英単語穴埋め問題の不正解選択肢の自動生成

    吉見 菜那, 梶原 智之, 内田 諭, 荒瀬 由紀, 二宮 崇

    言語処理学会 第29回年次大会 発表論文集   217 - 221   2023.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 学術ドメインに特化した日本語事前訓練モデルの構築

    山内 洋輝, 梶原 智之, 桂井 麻里衣, 大向 一輝, 二宮 崇

    言語処理学会 第29回年次大会 発表論文集   2842 - 2846   2023.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 単語の難易度埋め込みを用いた日本語のテキスト平易化

    柳本 大輝, 梶原 智之, 二宮 崇

    言語処理学会 第29回年次大会 発表論文集   1007 - 1011   2023.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 潜在拡散モデルによる変換画像を用いるマルチモーダルニューラル機械翻訳

    湯浅 亮也, 田村 晃裕, 梶原 智之, 二宮 崇, 加藤 恒夫

    言語処理学会 第29回年次大会 発表論文集   482 - 487   2023.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • バイリンガルサブワード分割のためのEMアルゴリズム

    松井 大樹, 二宮 崇, 田村 晃裕

    言語処理学会 第29回年次大会 発表論文集   1469 - 1473   2023.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 擬似データを用いた教師あり学習による語彙平易化

    野口 夏希, 梶原 智之, 荒瀬 由紀, 内田 諭, 二宮 崇

    言語処理学会 第29回年次大会 発表論文集   1012 - 1016   2023.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 異なる難易度の参照文を用いる多段階難易度制御翻訳

    谷 和樹, 湯浅 亮也, 田村 晃裕, 梶原 智之, 二宮 崇, 加藤 恒夫

    言語処理学会 第29回年次大会 発表論文集   3081 - 3086   2023.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 所見文書の要約を用いた深層学習による矯正歯科治療の自動診断

    大塚, 琢生, 梶原, 智之, 谷川, 千尋, 清水, 優仁, 長原, 一, 二宮, 崇

    第85回全国大会講演論文集   2023 ( 1 )   761 - 762   2023.2

     More details

    Language:Japanese  

    本研究では、深層学習に基づく自然言語処理の技術を用いて、矯正歯科治療における所見文書からの自動診断を行う。長文かつノイジーな所見文書から正確な診断を行うのは困難であるため、我々は所見文書の要約を用いて自動診断の性能を改善する。我々の先行研究では、BoW モデルを用いて専門医と同等の品質で自動診断を実現できることを示していたが、本研究の評価実験では、CNN モデルが更に高い性能を達成することを明らかにした。

    CiNii Books

    CiNii Research

    researchmap

  • Towards Parallel Corpus Filtering for Japanese Text Simplification

    畠垣光希, 梶原智之, 二宮崇

    情報科学技術フォーラム講演論文集   21st   2022

  • 多言語文符号化器の言語表現と意味表現の分離に基づく機械翻訳の品質推定

    黒田勇斗, 梶原智之, 荒瀬由紀, 二宮崇

    言語処理学会年次大会発表論文集(Web)   28th   2022

  • 主観と客観の感情極性分類のための日本語データセット

    宮内裕人, 鈴木陽也, 秋山和輝, 梶原智之, 二宮崇, 武村紀子, 中島悠太, 長原一

    言語処理学会年次大会発表論文集(Web)   28th   2022

  • QENTS:テキスト平易化の品質推定のためのデータセット

    廣中勇希, 井川朋樹, 梶原智之, 二宮崇

    言語処理学会年次大会発表論文集(Web)   28th   2022

  • 多段階難易度制御ニューラル機械翻訳のためのベンチマーク評価データセットの開発

    谷和樹, 湯浅亮也, 滝川一毅, 田村晃裕, 梶原智之, 二宮崇, 加藤恒夫

    言語処理学会年次大会発表論文集(Web)   28th   2022

  • スタイル変換のためのスタイルを考慮したSeq2Seq事前訓練

    松浦駿平, 梶原智之, 二宮崇

    言語処理学会年次大会発表論文集(Web)   28th   2022

  • Reinforcement Learning using Sentence-Level Difficulty for Text Simplification

    IKAWA Tomoki, KAJIWARA Tomoyuki, NINOMIYA Takashi

    Proceedings of the Annual Conference of JSAI   JSAI2022   2B5GS603 - 2B5GS603   2022

     More details

    Language:Japanese   Publisher:The Japanese Society for Artificial Intelligence  

    Text simplification is a natural language processing task that transforms complex text into simple text while preserving its meaning. People with language disabilities, children, and language learners can benefit from text simplification. Since audiences have different abilities and the difficulty needs to be adjusted according to their ability, some studies have proposed text simplification methods with controllable difficulty. However, previous methods are based on word-level difficulty and do not consider sentence-level difficulty. Accordingly, our approach uses reinforcement learning using a sentence-level difficulty estimator. Experiments results showed that the proposed method improves SARI, an automatic evaluation metric for text simplification.

    DOI: 10.11517/pjsai.jsai2022.0_2b5gs603

    CiNii Research

    researchmap

  • Emotional Intensity Estimation based on Writer’s Personality Information

    SUZUKI Haruya, AKIYAMA Kazuki, KAJIWARA Tomoyuki, NINOMIYA Takashi, TAKEMURA Noriko, NAKASHIMA Yuta, NAGAHARA Hajime

    Proceedings of the Annual Conference of JSAI   JSAI2022   4D3GS604 - 4D3GS604   2022

     More details

    Language:Japanese   Publisher:The Japanese Society for Artificial Intelligence  

    Emotion analysis is a natural language processing task that predicts human emotional intensity from the text. Previous emotion analysis models cannot adequately estimate the writer's emotion (subjective emotion). In this study, we specialize our emotion analysis model to estimate the subjective emotional intensity by considering the writer's personality information. Experimental results on the emotional intensity estimation of Plutchik's eight basic emotions in Japanese showed that the proposed method improves the performance of the estimation of subjective emotional intensity.

    DOI: 10.11517/pjsai.jsai2022.0_4d3gs604

    CiNii Research

    researchmap

  • A Survey of Machine Translation Technologies for Machine Translation on Patent Documents Reviewed

    Imamura Kenji, Echizen-ya Hiroshi, Ehara Terumasa, Goto Isao, Sudoh Katsuhito, Sonoh Satoshi, Tsunakawa Takashi, Nakazawa Toshiaki, Ninomiya Takashi, Wang Xiangli

    Journal of Natural Language Processing   29 ( 3 )   925 - 985   2022

     More details

    Language:Japanese   Publishing type:Article, review, commentary, editorial, etc. (scientific journal)   Publisher:The Association for Natural Language Processing  

    This survey paper reviews machine translation technologies for patent documents. Patent machine translation has been studied for a long time and has evolved by recent neural machine translation. This paper focuses on the following issues with future directions: under- and over translation, consistent technical term translation, long sentence translation, low-resource language pairs, evaluation, efficiency in speed and memory.

    DOI: 10.5715/jnlp.29.925

    CiNii Research

    researchmap

  • A Study of Reward Functions Suitable for Reinforcement Learning in Machine Translation

    NAKATANI Yuki, KAJIWARA Tomoyuki, NINOMIYA Takashi

    Proceedings of the Annual Conference of JSAI   JSAI2022   1P4GS604 - 1P4GS604   2022

     More details

    Language:Japanese   Publisher:The Japanese Society for Artificial Intelligence  

    In text generation tasks such as machine translation, models are generally trained using cross-entropy loss.However, mismatches between the loss function and the evaluation metric are often problematic.It is known that this problem can be addressed by direct optimization to the evaluation metric with reinforcement learning.In machine translation, previous studies have used BLEU to calculate rewards for reinforcement learning, but BLEU is not well correlated with human evaluation.In this study, we investigate the impact on machine translation quality through reinforcement learning based on evaluation metrics that are more highly correlated with human evaluation.Experimental results show that reinforcement learning based on BERT trained on the STS task can improve various evaluation metrics.

    DOI: 10.11517/pjsai.jsai2022.0_1p4gs604

    CiNii Research

    researchmap

  • 画像生成による疑似教師データを用いたマルチモーダルニューラル機械翻訳

    岩本裕司, 田村晃裕, 二宮崇

    言語処理学会年次大会発表論文集(Web)   27th   2021

  • 逆順デコーダを用いた係り受け構造に基づくTransformerニューラル機械翻訳

    佐々木拓馬, 田村晃裕, 出口祥之, 二宮崇, 加藤恒夫

    言語処理学会年次大会発表論文集(Web)   27th   2021

  • ニューラル機械翻訳のためのアテンション確率のスムージングとゲーティング学習

    張瀟廬, 二宮崇, 田村晃裕

    言語処理学会年次大会発表論文集(Web)   27th   2021

  • 同期注意制約を与えた依存構造に基づくTransformer NMT

    出口祥之, 田村晃裕, 二宮崇

    言語処理学会年次大会発表論文集(Web)   27th   2021

  • Hie-BART:階層型BARTによる文書要約

    秋山和輝, 田村晃裕, 二宮崇

    言語処理学会年次大会発表論文集(Web)   27th   2021

  • Introduction of AAMT Nagao Award and Student Award

    Ninomiya Takashi

    Journal of Natural Language Processing   28 ( 4 )   1342 - 1348   2021

     More details

    Language:Japanese   Publisher:The Association for Natural Language Processing  

    DOI: 10.5715/jnlp.28.1342

    CiNii Research

    researchmap

  • ニューラル機械翻訳のためのバイリンガルサブワード分割の研究—Studies on Bilingual Subword Segmentation for Neural Machine Translation—機械翻訳技術の向上

    二宮 崇, 出口 祥之, 内山 将夫, 田村 晃裕, 隅田 英一郎

    Japio year book   276 - 284   2021

     More details

    Language:Japanese   Publisher:日本特許情報機構  

    CiNii Research

    researchmap

  • R. B. について

    二宮 崇

    自然言語処理   28 ( 4 )   936 - 937   2021

     More details

    Language:Japanese   Publisher:一般社団法人 言語処理学会  

    DOI: 10.5715/jnlp.28.936

    CiNii Research

    researchmap

  • 画像生成による擬似教師データを用いたマルチモーダル機械翻訳

    岩本 裕司, 田村 晃裕, 二宮 崇

    情報処理学会研究報告 自然言語処理 (NL)   2020-NL-246 ( 6 )   1 - 6   2020.11

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • ニューラル機械翻訳のためのバイリンガルなサブワード分割

    出口 祥之, 内山 将夫, 田村 晃裕, 二宮 崇, 隅田 英一郎

    情報処理学会研究報告 自然言語処理 (NL)   2020-NL-246 ( 22 )   1 - 8   2020.11

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • Coverageを考慮したBERTSUMによる生成型自動要約

    秋山 和輝, 田村 晃裕, 二宮 崇, 大林 弘明

    言語処理学会 第26回年次大会 発表論文集   449 - 452   2020.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 同期注意制約を与えたTransformerによるニューラル機械翻訳

    出口 祥之, 田村 晃裕, 二宮 崇

    言語処理学会 第26回年次大会 発表論文集   1459 - 1462   2020.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 文レベルの中間表現とのアテンションを用いたニューラル機械翻訳

    福原 健太, 田村 晃裕, 二宮 崇

    言語処理学会 第26回年次大会 発表論文集   1289 - 1292   2020.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 注意機構制約を用いたマルチモーダルNMT

    西原 哲郎, 田村 晃裕, 二宮 崇, 中山 英樹

    言語処理学会 第26回年次大会 発表論文集   1463 - 1466   2020.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 発話の位置情報を考慮した対話行為認識

    矢野 祐貴, 田村 晃裕, 二宮 崇, 大林 弘明

    言語処理学会 第26回年次大会 発表論文集   1081 - 1084   2020.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 教師付き注意機構を用いた文法誤り訂正

    石井 宏道, 田村 晃裕, 二宮 崇

    言語処理学会 第26回年次大会 発表論文集   889 - 892   2020.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • Transformerを用いた化合物名から化学構造への変換

    表 悠太郎, 松下 京群, 岩倉 友哉, 田村 晃裕, 二宮 崇

    言語処理学会 第26回年次大会 発表論文集   1161 - 1164   2020.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 機械翻訳のための係り受け構造に基づくトランスフォーマーモデルの研究

    二宮 崇, 表 悠太朗, 出口 祥之, 田村 晃裕

    Japio YEAR BOOK 2019   280 - 287   2019.11

     More details

    Language:Japanese   Publishing type:Article, review, commentary, editorial, etc. (bulletin of university, research institution)  

    researchmap

  • 自己符号化器によるニューラル機械翻訳モデルの分野適応

    中川 靖久, 田村 晃裕, 二宮 崇

    令和元年度電気関係学会四国支部連合大会 講演論文集   167 - 167   2019.9

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 教師あり注意機構を用いた文法誤り訂正

    石井 宏道, 田村 晃裕, 二宮 崇

    令和元年度電気関係学会四国支部連合大会 講演論文集   168 - 168   2019.9

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 敵対的生成ネットワークを用いた教師なし画像キャプション生成

    田辺 裕次郎, 田村 晃裕, 二宮 崇

    令和元年度電気関係学会四国支部連合大会 講演論文集   170 - 170   2019.9

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • Raspberry Piを用いた画像処理とCNNによる微小害虫の計数システムの構築

    阿部 寛人, 畝山 勇一朗, 中岡 典弘, 渡辺 友希, 福本 真也, 森田 航平, 中本 裕大, 周 細紅, 河野 靖, 木下 浩二, 一色 正晴, 二宮 崇, 田村 晃裕, 甲斐 博, 高橋 寛, 王 森レイ

    令和元年度電気関係学会四国支部連合大会論文集(CD-ROM)   2019   2019.9

     More details

    Publishing type:Research paper, summary (national, other academic conference)  

    J-GLOBAL

    researchmap

  • 物体間の関係性を考慮したTransformerに基づくキャプション生成

    中本 裕大, 田村 晃裕, 二宮 崇

    言語処理学会 第25回年次大会 発表論文集   759 - 762   2019.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 人工負例による識別器を用いたニューラル機械翻訳

    白井 圭佑, 橋本 和真, 江里口 瑛子, 森 信介, 二宮 崇

    言語処理学会 第25回年次大会 発表論文集   105 - 108   2019.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 係り受け構造に基づくAttentionの制約を用いたNMT

    出口 祥之, 田村 晃裕, 二宮 崇

    言語処理学会 第25回年次大会 発表論文集   13 - 16   2019.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • CNNとTransformerエンコーダを用いたマルチモーダルニューラル機械翻訳

    宅島 寛貴, 田村 晃裕, 二宮 崇, 中山 英樹

    言語処理学会 第25回年次大会 発表論文集   743 - 746   2019.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 係り受け構造に対する相対位置表現を考慮したNMT

    表 悠太郎, 田村 晃裕, 二宮 崇

    言語処理学会 第25回年次大会 発表論文集   611 - 614   2019.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 化合物の同義語辞書を用いた固有表現抽出

    渡邊 大貴, 田村 晃裕, 二宮 崇, 牧野 拓哉, 岩倉 友哉

    言語処理学会 第25回年次大会 発表論文集   767 - 770   2019.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • enPiT-Pro Embにおける社会人教育実践とその評価

    名倉正剛, 高田広章, 山本雅基, 塩見彰睦, 野口靖浩, 岡村寛之, 高橋寛, 一色正晴, WANG Senling, 甲斐博, 木下浩二, 田村晃裕, 二宮崇, 沢田篤史

    教育システム情報学会全国大会講演論文集(CD-ROM)   44th   2019

  • 機械学習を応用した軌道回路の状態基準保全に関する研究

    志田洋, 田村晃裕, 二宮崇, 高橋寛

    日本機械学会 第25回鉄道技術連合シンポジウム   25th   2307   2018.12

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)   Publisher:The Japan Society of Mechanical Engineers  

    The track circuit is an important equipment for the railway operation to be safe and reliable. The maintenance of the currently used track circuit is based on the Time Based Maintenance (TBM). However, TBM has a problem to require excessive maintenance. Therefore we focus on the Condition Based Maintenance (CBM), which expects the reduced cost for maintaining the equipment. In this paper, we propose a maintenance method of the track circuit applying Machine Learning, which finds an appropriate time to perform the maintenance.

    DOI: 10.1299/jsmetld.2018.27.2307

    CiNii Research

    researchmap

  • ニューラルネットワークによる軌道回路の状態基準保全に関する考察

    志田 洋, 田村 晃裕, 二宮 崇, 高橋 寛

    日本信頼性学会第26回春季信頼性シンポジウム   2018.6

     More details

    Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 双方向翻訳のための中間表現制約を用いたニューラル機械翻訳

    小林 尚輝, 田村 晃裕, 二宮 崇, 高村 大也, 奥村 学

    言語処理学会 第24回年次大会 発表論文集   300 - 303   2018.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 画像物体間の構造情報を用いた深層学習によるキャプション生成

    野口 敬輔, 二宮 崇, 田村 晃裕

    言語処理学会 第24回年次大会 発表論文集   384 - 387   2018.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • Gumbel Samplingを用いた敵対性ニューラル機械翻訳

    白井 圭佑, 江里口 瑛子, 橋本 和真, 森 信介, 二宮 崇

    言語処理学会 第24回年次大会 発表論文集   296 - 299   2018.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 単語の多義性を考慮した対訳単語対の抽出

    中本 裕大, 田村 晃裕, 二宮 崇

    言語処理学会 第24回年次大会 発表論文集   710 - 713   2018.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 固有表現情報を用いたニューラル機械翻訳

    鵜川 新, 田村 晃裕, 二宮 崇, 高村 大也, 奥村 学

    言語処理学会 第24回年次大会 発表論文集   25 - 28   2018.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 軌道回路の状態基準保全に向けた検討(その3)-設備故障の再現試験とマハラノビス距離による設備の劣化把握-

    志田 洋, 二宮 崇, 高橋 寛

    日本信頼性学会第30回秋季信頼性シンポジウム   2017.11

     More details

    Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 深層学習による柑橘類果実の個数推定

    野口 敬輔, 小川 達也, 安保 良佑, 高原 圭太, 河野 靖, 木下 浩二, 二宮 崇, 田村 晃裕, 高橋 寛, 王 森レイ, 樋上 善信, 藤田 欣裕, 二宮 宏

    平成29年度 電気関係学会四国支部連合大会 講演論文集   177 - 177   2017.9

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 画像処理と深層学習による微小害虫の検出

    中浦 大貴, 渡邊 大貴, 増成 紳介, 矢野 良典, 河野 靖, 木下 浩二, 二宮 崇, 田村 晃裕, 高橋 寛, 王 森レイ, 樋上 喜信, 藤田 欣裕, 二宮 宏

    平成29年度 電気関係学会四国支部連合大会 講演論文集   183 - 183   2017.9

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 軌道回路の状態基準保全に向けた検討(その2)‐機械学習による設備状態のトレンド分析-

    志田 洋, 武市 徹, 大串 裕郁, 二宮 崇, 高橋 寛

    日本信頼性学会第25回春季信頼性シンポジウム   2017.5

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 敵対性学習を用いたニューラル機械翻訳

    白井 圭佑, 二宮 崇, 森 信介

    言語処理学会 第23回年次大会 発表論文集   1105 - 1108   2017.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 統計的機械翻訳のための確率比を用いたリサンプリングによるドメイン適応

    野口 敬輔, 二宮 崇

    言語処理学会 第22回年次大会 発表論文集   701 - 704   2016.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 深層学習を用いた実世界参照による分野特有の固有表現の認識

    友利 涼, 二宮 崇, 森 信介

    言語処理学会 第22回年次大会 発表論文集   801 - 804   2016.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 言語概念ベクトルを用いた文書間類似度に基づく複数文書自動要約

    住田 恭平, 二宮 崇

    言語処理学会 第22回年次大会 発表論文集   513 - 516   2016.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • word2vecと深層学習を用いた大規模評判分析

    加藤 和平, 大島 孝範, 二宮 崇

    言語処理学会 第21回年次大会 発表論文集   525 - 528   2015.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • word2vecに基づく述語項構造の分布表現獲得

    岩井 美樹, 二宮 崇

    言語処理学会 第21回年次大会 発表論文集   75 - 78   2015.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • ロジスティック回帰の学習におけるパラメータ平均化

    秋山 健人, 二宮 崇

    平成26年度 電気関係学会四国支部連合大会 講演論文集   242 - 242   2014.9

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 英語学習者コーパスとウェブNグラムを用いた文法誤り検出

    佐伯 卓哉, 二宮 崇

    平成26年度 電気関係学会四国支部連合大会 講演論文集   243 - 243   2014.9

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • ロジスティック回帰におけるパラメータ平均化

    秋山 健人, 二宮 崇

    2014年度人工知能学会全国大会(第28回) 論文集   3O1-5in   1 - 4   2014.5

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • Application of Integer Linear Programming to BBS Summarization

    3I3-2   1 - 4   2014.5

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    CiNii Books

    researchmap

  • 最大被覆モデルを用いた電子掲示板の自動要約

    田中 駿, 矢野 裕一朗, 二宮 崇, 高村 大也

    言語処理学会 第20回年次大会 発表論文集   500 - 503   2014.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • シンポジウム報告 第14回機械翻訳サミット (Machine Translation Summit XIV) および第5回特許翻訳ワークショップ (The 5th Workshop on Patent Translation) 参加報告 Invited

    横山 晶一, 梶 博行, 二宮 崇

    AAMTジャーナル   ( 54 )   39 - 43   2013.10

     More details

    Language:Japanese   Publishing type:Meeting report  

    researchmap

  • 格解析を用いた助詞の表層格変換による統計機械翻訳の高精度化

    田中 飛馬, 二宮 崇

    平成25年度 電気関係学会四国支部連合大会 講演論文集   327 - 327   2013.9

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • EHIME Texutual Entailment System Using Markov Logic in NTCIR-10 RITE-2

    Yuji Takesue, Takashi Ninomiya

    Proceedings of the 10th NTCIR Conference   507 - 511   2013.6

     More details

    Language:English   Publishing type:Research paper, summary (international conference)  

    researchmap

  • カテゴリ毎に異なるナイーブベイズ分類器を用いた大規模評判分析

    岩田 匠, 二宮 崇

    平成24年度 電気関係学会四国支部連合大会 講演論文集   285 - 285   2012.9

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • ディリクレ事前分布付き隠れマルコフモデルにおけるスムージング効果の調査

    矢野 裕一朗, 二宮 崇

    平成24年度 電気関係学会四国支部連合大会 講演論文集   286 - 286   2012.9

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • Towards Synchronous Head-driven Phrase Structure Grammars

    11   178 - 183   2012.3

     More details

    Language:Japanese   Publishing type:Rapid communication, short report, research note, etc. (bulletin of university, research institution)  

    CiNii Books

    researchmap

  • シーズ(研究成果)探訪 vol.81, データの自動分類とテキストの構文解析―高速化と高精度化― 自動的に特徴を学習するオンライン学習と言語学的文法に基づく構文解析 Invited

    二宮 崇

    月刊愛媛ジャーナル   25 ( 7 )   80 - 82   2011.12

     More details

    Language:Japanese   Publishing type:Article, review, commentary, editorial, etc. (trade magazine, newspaper, online media)  

    researchmap

  • シンポジウム報告 MT Summit XIII参加報告 Invited

    二宮 崇, 横山晶一

    AAMTジャーナル   ( 50 )   2 - 3   2011.12

     More details

    Language:Japanese   Publishing type:Meeting report  

    researchmap

  • オンライングラフティングのパラメータ平均化による集合型学習

    大井 健吾, 二宮 崇

    平成23年度 電気関係学会四国支部連合大会 講演論文集   258 - 258   2011.9

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • オンライングラフティングのアンサンブル学習

    大井健吾, 二宮崇

    情報処理学会 第73回全国大会講演論文集   1 ( 1 )   301 - 302   2011.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    機械学習における識別モデルの特徴関数は人手による試行錯誤で設計されているが、数十万から数百万に及ぶ特徴関数を人手で発見・制御することは非常に困難な作業となっている。本研究は、特徴関数を逐次的に選択・構築しつつ目的関数を最適化するオンライングラフティングに対するアンサンブル学習の研究を行う。グラフティングは一般に、訓練データに対する過学習の問題が知られているが、アンサンブル学習により高精度かつ汎化性能の高い学習を行う。このモデルを用いた実験、評価を行う。

    CiNii Books

    researchmap

  • A reading support system for English Wikipedia with prediction capability of the words unknown to the users

    EHARA YO, NINOMIYA TAKASHI, SHIMIZU NOBUYUKI, NAKAGAWA HIROSHI

    2010-HCI-138 ( 4 )   1 - 6   2010.5

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    CiNii Books

    researchmap

  • A reading support system for Web pages with prediction capability of the words unknown to users

    2F1-04   1 - 4   2010.5

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    CiNii Books

    researchmap

  • A reading support tool with prediction capability and its extension to readability measurement

    EHARA YO, NINOMIYA TAKASHI, SHIMIZU NOBUYUKI, NAKAGAWA HIROSHI

    2010-NL-196, 2010-SLP-81 ( 18 )   1 - 7   2010.5

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    CiNii Books

    researchmap

  • Exact PA Algorithms for online learning on multi-class classification problem

    MATSUSHIMA Shin, SHIMIZU Nobuyuki, YOSHIDA Kazuhiro, NINOMIYA Takashi, NAKAGAWA Hiroshi

    2   467 - 468   2010.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    CiNii Books

    researchmap

  • Web文書中のユーザが知らない語を予測する読解支援システム

    江原 遥, 二宮 崇, 清水 伸幸, 中川 裕志

    情報処理学会創立50周年記念 (第72回) 全国大会講演論文集   2   77 - 78   2010.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    CiNii Books

    researchmap

  • 英語版Wikipediaを対象としたユーザが知らない語を予測する読解支援システム

    江原 遥, 清水 伸幸, 二宮 崇, 中川 裕志

    言語処理学会 第16回年次大会 発表論文集   2010.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • Online Semisupervised Learning on Multiclass Classificatio

    MATSUSHIMA SHIN, SHIMIZU NOBUYUKI, SATO ISSEI, NINOMIYA TAKASHI, NAKAGAWA HIROSHI

    2009-MPS-76, 2009-BIO-19 ( 21 )   1 - 8   2009.12

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    CiNii Books

    researchmap

  • A Predictor of Words Unknown to Users by Analyzing Clicked Word Logs

    EHARA YO, NINONIMIYA TAKASHI, NAKAGAWA HIROSHI

    2009-NL-193 ( 3 )   1 - 7   2009.9

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    CiNii Books

    researchmap

  • Multi-Class Passive-Aggressive Algorithm with Support Classes

    MATSUSHIMA SHIN, SHIMIZU NOBUYUKI, YOSHIDA KAZUHIRO, NINOMIYA TAKASHI, NAKAGAWA HIROSHI

    2009-NL-192 ( 12 )   1 - 6   2009.7

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    CiNii Books

    researchmap

  • 機械学習による自動辞書引きを利用した英文の読解支援システム

    江原 遥, 二宮 崇, 中川 裕志

    言語処理学会 第15回年次大会 発表論文集   885 - 888   2009.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 機械学習テンプレートライブラリを用いた英語品詞タガー

    松島 慎, 清水 伸幸, 二宮 崇, 中川裕志

    NLP若手の会第3回シンポジウム   2008.9

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 辞書引き履歴のソーシャル化による学習者支援

    江原 遥, 二宮 崇, 中川裕志

    言語処理学会 第14回年次大会併設ワークショップ「教育・学習を支援する言語処理」   2008.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 機械学習を用いた文脈自由規則の書き換えによる文圧縮

    海野 裕也, 二宮 崇, 宮尾 祐介, 辻井 潤一

    言語処理学会第12回年次大会発表論文集   1091 - 1094   2006.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 領域代数を用いた構造化テキスト検索の頑健でスケーラブルなモデル

    増田 勝也, 二宮 崇, 宮尾 祐介, 辻井 潤一

    言語処理学会第10回年次大会発表論文集   377 - 380   2004.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 情報検索のためのトピック適応型単語クラスタリング

    綱川 隆司, 二宮 崇, 宮尾 祐介, 辻井 潤一

    言語処理学会第10回年次大会発表論文集   21 - 24   2004.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 語彙化文法における語彙項目の構造的特徴に基づく自動分類

    大内田 賢太, 吉永 直樹, 二宮 崇, 宮尾 祐介, 辻井 潤一

    言語処理学会第9回年次大会論文集   553 - 556   2003.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • GCL問い合わせ代数による構造化テキストのランク検索

    増田 勝也, 二宮 崇, 辻井潤一

    言語処理学会第8回年次大会発表論文集   459 - 462   2002.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • A Structure of Interpreting Route Instructions with Reference Positions

    16   1 - 3   2002

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    DOI: 10.11517/pjsai.JSAI02.0.185.0

    CiNii Books

    researchmap

  • 高速FB-LTAGパーザとその並列化

    吉田 稔, 二宮 崇, 鳥澤 健太郎, 辻井 潤一

    言語処理学会第5回年次大会発表論文集   96 - 99   1999.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • Practical HPSG Parsers

    Kentaro Torisawa, Takaki Makino, Minoru Yoshida, Takashi Ninomiya, Kenji Nishida, Hisao Imai, Yutaka Mitsuishi, Hiroshi Kanayama, Yuka Tateisi, Yusuke Miyao, Jun'ichi Tsujii

    Proceedings of JSPS Symposium on Intelligent Information and Advanced Information Processing   46 - 50   1999

     More details

    Publishing type:Research paper, summary (international conference)  

    researchmap

  • Practical HPSG Parsers

    Kentaro Torisawa, Takaki Makino, Takashi Ninomiya, Yutaka Mitsuisi, Yuka Tateishi, Kenji Nishida, Yusuke Miyao, Minoru Yoshida, Jun-ichi Tsujii

    Proceedings of JSPS-HITACHI Workshop on New Challenges in Natural Language Processing and its Application   100 - 105   1998.5

     More details

    Language:English   Publishing type:Research paper, summary (international conference)  

    researchmap

  • 並列HPSGパーザー

    二宮 崇, 鳥澤 健太郎, 辻井 潤一

    言語処理学会第4回年次大会発表論文集   101 - 104   1998.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • Towards a Concurrent HPSG Parser

    NINOMIYA Takashi, TORISAWA Kentaro, TAURA Kenjiro, TSUJII Jun'ichi

    IPSJ SIG Notes   1997-NL-117 ( 4 )   75 - 81   1997.1

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)   Publisher:Information Processing Society of Japan (IPSJ)  

    This paper describes an attempt to develop a parallel parsing algorithm for Torisawa's parsing algorithm for HPSG. Torisawa's algorithm consists of two phases. At Phase 1, a parser enumerates possible parse trees using CFG rules compiled from lexical entries in HPSG. The constraints uncovered by the CFG are solved at Phase 2, using feature structures and a variant of unification, partial unification. We realized a parallel parsing algorithm for Phase1, on a highly parallel computer AP1000+(256Super Sparc 50Mhz) with concurrent object-oriented programming language ABCl/f. The average parsing time for the sentences consisting of less than 50 words was 98 msec.

    CiNii Books

    researchmap

  • 並列オブジェクト指向言語ABCL/fにおけるスケーラブルな並列CKYアルゴリズム

    二宮崇

    オブジェクト指向コンピューティングワークショップ(WOOC)予稿集   1997

     More details

▼display all

Presentations

  • 人工知能と自然言語処理の発展 Invited

    二宮 崇

    令和4年度第2回愛媛大学工学部附属船舶海洋工学センター技術連絡会  2023.3 

     More details

    Language:Japanese   Presentation type:Public lecture, seminar, tutorial, course, or other speech  

    researchmap

  • 感情極性分類と感情強度推定の同時学習の検討

    樽本空宙, 鈴木 陽也, 梶原 智之, 二宮 崇, 中島 悠太, 長原 一

    NLP若手の会第17回シンポジウム  2022.8 

     More details

    Language:Japanese   Presentation type:Poster presentation  

    researchmap

  • 機械翻訳のための言い換え生成による前編集の検討

    惟高 日向, 岩本 裕司, 梶原 智之, 二宮 崇, 藤田 篤

    NLP若手の会第17回シンポジウム  2022.8 

     More details

    Language:Japanese   Presentation type:Poster presentation  

    researchmap

  • 大規模言語モデルによる日本語テキスト平易化のためのパラレルコーパスフィルタリング

    前川大輔, 梶原智之, 二宮崇

    NLP若手の会 第19回シンポジウム  2024.9 

     More details

    Language:Japanese   Presentation type:Poster presentation  

    researchmap

  • Recent Advances in Natural Language Processing and Multimodal Machine Translation Invited

    Takashi Ninomiya

    Seminar at Vietnam National University, HCMC, University of Information Technology  2024.5 

     More details

    Language:English   Presentation type:Public lecture, seminar, tutorial, course, or other speech  

    researchmap

  • 商品検索のための追加事前学習としての言い換えに基づく対照学習

    杉山誠治, 近藤里咲, 梶原智之, 二宮崇

    NLP若手の会 第19回シンポジウム  2024.9 

     More details

    Language:Japanese   Presentation type:Poster presentation  

    researchmap

  • 大規模言語モデルによる11種類の日本語スタイル変換の性能評価

    花房健太郎, 柳本大輝, 梶原智之, 二宮崇

    NLP若手の会 第19回シンポジウム  2024.9 

     More details

    Language:Japanese   Presentation type:Poster presentation  

    researchmap

  • テキスト生成AI~ChatGPTが開いた新しい世界~ Invited

    二宮 崇

    愛媛赤門会  2024.3 

     More details

    Language:Japanese   Presentation type:Public lecture, seminar, tutorial, course, or other speech  

    researchmap

  • ニューラル単語アライメントによる言い換え辞書の改善

    近藤里咲, 梶原智之, 二宮崇

    NLP若手の会 第19回シンポジウム  2024.9 

     More details

    Language:Japanese   Presentation type:Poster presentation  

    researchmap

  • 情報科学分野における学会発表タイトルの分野推定データセットの構築

    宮田莉奈, 眞鍋光汰, 福島啓太, 花房健太郎, 高田一慶, 梶原智之, 桂井麻里衣, 二宮崇

    NLP若手の会 第19回シンポジウム  2024.9 

     More details

    Language:Japanese   Presentation type:Poster presentation  

    researchmap

  • 大規模言語モデルによる機械翻訳の教師なし品質推定

    樽本空宙, 梶原智之, 二宮崇

    NLP若手の会 第19回シンポジウム  2024.9 

     More details

    Language:Japanese   Presentation type:Poster presentation  

    researchmap

  • 問題タイプを考慮した教師あり学習による英単語穴埋め問題の自動生成

    吉見菜那, 梶原智之, 内田諭, 荒瀬由紀, 二宮崇

    NLP若手の会 第19回シンポジウム  2024.9 

     More details

    Language:Japanese   Presentation type:Poster presentation  

    researchmap

  • テキスト生成AI~ChatGPTとOpen LLMが開く新しい世界~ Invited

    二宮 崇

    愛媛大学第23回学術フォーラム  2024.10 

     More details

    Language:Japanese   Presentation type:Public lecture, seminar, tutorial, course, or other speech  

    researchmap

  • HPSG 構文解析とスーパータガー Invited

    二宮 崇

    愛媛大学数学談話会  2011.10 

     More details

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    researchmap

  • 英単語穴埋め問題における選択肢の自動生成に向けて

    吉見 菜那, 廣中 勇希, 梶原 智之, 荒瀬 由紀, 内田 諭, 二宮 崇

    NLP若手の会第17回シンポジウム  2022.8 

     More details

    Language:Japanese   Presentation type:Poster presentation  

    researchmap

  • 文法開発の方法論について Invited

    二宮 崇

    東京大学創造情報学専攻セミナー(実践工房)  2013.7 

     More details

    Language:Japanese   Presentation type:Public lecture, seminar, tutorial, course, or other speech  

    researchmap

  • 語義注釈システムの単語クリックログからの言語能力情報の抽出

    江原 遥, 二宮 崇, 中川 裕志

    NLP若手の会 第4回シンポジウム  2009.9 

     More details

    Language:Japanese   Presentation type:Poster presentation  

    researchmap

  • HMMにおけるアンサンブル学習

    黒澤 雅人, 佐藤 一誠, 松島 慎, 二宮 崇, 中川 裕志

    NLP若手の会 第5回シンポジウム  2010.9 

     More details

    Language:Japanese   Presentation type:Oral presentation (general)  

    researchmap

  • ソーシャル辞書:語学学習における協調フィルタリングを用いた学習単語の推薦

    江原 遥, 二宮 崇, 中川裕志

    NLP若手の会 第3回シンポジウム  2008.9 

     More details

    Language:Japanese   Presentation type:Poster presentation  

    researchmap

  • 自然言語処理における文法開発の軌跡と展望 Invited

    二宮 崇, 宮尾祐介

    言語処理学会第13回年次大会チュートリアル  2007.3 

     More details

    Language:Japanese   Presentation type:Public lecture, seminar, tutorial, course, or other speech  

    researchmap

  • 所見文書の要約を用いた矯正歯科治療の自動診断の検討

    大塚琢生, 梶原 智之, 谷川 千尋, 清水 優仁, 長原 一, 二宮 崇

    NLP若手の会第17回シンポジウム  2022.8 

     More details

    Language:Japanese   Presentation type:Poster presentation  

    researchmap

  • ユーザの性格情報を用いた感情分析

    鈴木 陽也, 梶原 智之, 二宮 崇, 中島 悠太, 長原 一

    NLP若手の会第17回シンポジウム  2022.8 

     More details

    Language:Japanese   Presentation type:Poster presentation  

    researchmap

  • 人工知能の最前線~深層学習の衝撃と発展の経緯~ Invited

    二宮 崇

    大洲・喜多経済研究会  2019.3 

     More details

    Language:Japanese   Presentation type:Public lecture, seminar, tutorial, course, or other speech  

    researchmap

  • 学術ドメインに特化した日本語マスク言語モデルの試作

    山内 洋輝, 梶原 智之, 桂井 麻里衣, 大向 一輝, 二宮 崇

    NLP若手の会第17回シンポジウム  2022.8 

     More details

    Language:Japanese   Presentation type:Poster presentation  

    researchmap

  • 人工知能の最前線~深層学習の衝撃~ Invited

    二宮 崇

    今治経済研究会  2018.5 

     More details

    Language:Japanese   Presentation type:Public lecture, seminar, tutorial, course, or other speech  

    researchmap

  • Project Introduction: Multimodal Context Understanding for Neural Machine Translation Invited

    Takashi Ninomiya

    Traitement Sémantique des Données Textuelles (TALSEM) Séminaire  2018.10 

     More details

    Language:English   Presentation type:Public lecture, seminar, tutorial, course, or other speech  

    researchmap

  • 人工知能と深層学習 Invited

    二宮 崇

    四国総合研究所 社内AI技術勉強会  2018.3 

     More details

    Language:Japanese   Presentation type:Public lecture, seminar, tutorial, course, or other speech  

    researchmap

  • シンボルグラウンディングと自然言語処理 Invited

    二宮 崇

    「all-words WSD システムの構築及び分類語彙表と岩波国語辞典の対応表作成への利用」研究発表会  2017.9 

     More details

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    researchmap

  • 人工知能の最前線~深層学習の衝撃と発展の経緯、深層学習でできること/できないこと~ Invited

    二宮 崇

    昭和会 平成30年2月例会  2018.2 

     More details

    Language:Japanese   Presentation type:Public lecture, seminar, tutorial, course, or other speech  

    researchmap

  • あなたの知らない地方国立大学 Invited

    二宮 崇

    言語処理学会 第22回年次大会ワークショップ「論文に書かない(書けない)自然言語処理」  2016.3 

     More details

    Language:Japanese   Presentation type:Oral presentation (general)  

    researchmap

  • 3年先を見据えたAI~機械学習と深層学習~ Invited

    二宮 崇

    愛媛ニアショア開発協議会 創立5周年通常総会・講演会  2017.7 

     More details

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    researchmap

  • 専門家が平易化した記事を用いたやさしい日本語パラレルコーパスの構築

    宮田 莉奈, 惟高 日向, 山内 洋輝, 柳本 大輝, 梶原 智之, 二宮 崇, 西脇 靖紘

    NLP若手の会第18回シンポジウム  2023.8 

     More details

    Language:Japanese   Presentation type:Poster presentation  

    researchmap

  • 雑談対話にキャラクタ性を付与するためのスタイル変換

    近藤 里咲, 梶川 怜恩, 梶原 智之, 二宮 崇

    NLP若手の会第18回シンポジウム  2023.8 

     More details

    Language:Japanese   Presentation type:Poster presentation  

    researchmap

  • 講演動画における英日字幕翻訳のためのマルチモーダル対訳コーパスの試作

    寺面 杏優, 梶原 智之, 二宮 崇

    NLP若手の会第18回シンポジウム  2023.8 

     More details

    Language:Japanese   Presentation type:Poster presentation  

    researchmap

  • 大規模言語モデルとChatGPT Invited

    二宮 崇

    愛媛県 拡大部局長会  2023.6 

     More details

    Language:Japanese   Presentation type:Public lecture, seminar, tutorial, course, or other speech  

    researchmap

▼display all

Awards

  • 人工知能学会 第38回全国大会 優秀賞

    2024.5   人工知能学会   テキスト正規化による日本語感情分析の性能改善

    近藤里咲, 寺面杏優, 梶川怜恩, 堀口航輝, 梶原智之, 二宮崇, 早志英朗, 中島悠太, 長原一

     More details

  • 愛媛大学 学長賞

    2023.10   愛媛大学  

    松浦 真也, 山内 貴光, 尾國 新一, 樋上 喜信, 二宮 崇, 甲斐 博

     More details

  • 言語処理学会 第29回年次大会 委員特別賞

    2023.3   言語処理学会   問題タイプを考慮した英単語穴埋め問題の不正解選択肢の自動生成

    吉見 菜那, 梶原 智之, 内田 諭, 荒瀬 由紀, 二宮 崇

     More details

  • 愛媛大学 学長賞

    2022.10   愛媛大学  

    森脇 亮, 井原 栄治, 黄木 景二, 小林 千悟, 二宮 崇, 小原 敬士, 松浦 真也, 前原 常弘, 井上 幹生, 鍔本 武久

     More details

  • 情報処理学会 第246回自然言語処理研究会 優秀研究賞

    2020.12   情報処理学会 自然言語処理研究会   ニューラル機械翻訳のためのバイリンガルなサブワード分割

    出口 祥之, 内山 将夫, 田村 晃裕, 二宮 崇, 隅田 英一郎

     More details

  • 言語処理学会 論文賞

    2020.3   言語処理学会   CKYに基づく畳み込みアテンション構造を用いたニューラル機械翻訳

    渡邊 大貴, 田村 晃裕, 二宮 崇, Teguh Bharata Adji

     More details

  • NLP若手の会第5回シンポジウム 奨励賞

    2010.9   NLP若手の会   HMMにおけるアンサンブル学習

    黒澤 雅人, 佐藤 一誠, 松島 慎, 二宮 崇, 中川 裕志

     More details

    Country:Japan

    researchmap

  • NLP若手の会第4回シンポジウム 奨励賞

    2009.9   NLP若手の会   語義注釈システムの単語クリックログからの言語能力情報の抽出

    江原 遥, 二宮 崇, 中川 裕志

     More details

    Country:Japan

    researchmap

▼display all

Research Projects

  • A Study on Neural Machine Translation based on Latent Diffusion Models

    2024.4 - 2027.3

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research  Grant-in-Aid for Scientific Research (C)

      More details

    Grant amount:\4680000 ( Direct Cost: \3600000 、 Indirect Cost:\1080000 )

    researchmap

  • マルチモーダル情報理解と制御可能なテキスト生成の研究開発

    2022.1 - 2026.3

    情報通信研究機構 (NICT)  自動翻訳の精度向上のための「マルチモーダル情報の外部制御可能なモデ リング」の研究開発 

    岡崎 直観, 高瀬 翔, 中山 英樹, 中澤 敏明, 二宮 崇, 梶原 智之, 後藤 功雄, 小町 守, 岡 照晃, 山田 一郎, 美野 秀弥, 衣川 和尭, 朝賀 英裕, 川上貴之

      More details

    Authorship:Coinvestigator(s) 

    researchmap

  • A Study on Context-aware Latent Variable Models for Neural Machine Translation

    2021.4 - 2024.3

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research  Grant-in-Aid for Scientific Research (C)

      More details

    Grant amount:\4160000 ( Direct Cost: \3200000 、 Indirect Cost:\960000 )

    researchmap

  • 深層学習によるマルチモーダル文脈理解と機械翻訳の高度化

    2018.7 - 2020.3

    情報通信研究機構(NICT)  多言語音声翻訳高度化のためのディープラーニング技術の研究開発 

    岡崎 直観, 高瀬 翔, 中山 英樹, 中澤 敏明, 鶴岡 慶雅, 二宮 崇, 田村 晃裕, 田中 英輝, 後藤 功雄, 美野 秀弥, 朝賀 英裕, 川上貴之

      More details

    Authorship:Coinvestigator(s)  Grant type:Competitive

    researchmap

  • Internal Erosion in a Foundation Soil under a Sand Levee and its Manifestation on the Levee Surface

    2017.6 - 2019.3

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research  Grant-in-Aid for Challenging Research (Exploratory)

    Mitsu Okamura

      More details

    Grant amount:\6370000 ( Direct Cost: \4900000 、 Indirect Cost:\1470000 )

    River levees occasionally fail during flooding because of the mechanics of internal erosion or piping within or below the levees. Current inspection methods cannot detect the pipes until it manifests itself at the exterior sur-face. There is a strong need for non-destructive techniques that can identify internal damage. In this study it was found that specific deformation pattern appears on the surface of levees just above pipes. A method was established for estimating the size and location of the pipes based on the characteristic shape of the de-formed slope. The method was applied to levees, where significant sand boils occurred at the levee toe during recent flooding events. In addition, a number of mini-ram soundings were conducted at small intervals to identify the pipe locations in a more direct manner. It was confirmed that the penetration tests were effective in detecting the pipe locations. The detected locations compared well with those estimated from the surface topography.

    researchmap

  • 実用的な日本語格解析のための確率的日本語主辞駆動句構造文法に関する研究

    2013.4 - 2018.3

    日本学術振興会  科学研究費補助金 基盤研究(B) 

    二宮 崇

      More details

    Authorship:Principal investigator  Grant type:Competitive

    researchmap

  • 高度構文解析技術を用いた統計機械翻訳の高精度化に関する研究

    2012.4 - 2013.3

    国立情報学研究所  平成24年度 国立情報学研究所 公募型共同研究 

    二宮 崇

      More details

    Authorship:Principal investigator  Grant type:Competitive

    researchmap

  • 構文木が付与された大規模英日パラレルコーパスの実現と検証

    2011.4 - 2012.3

    愛媛大学  平成23年度工学部長(理工学研究科工学系長)裁量研究支援費 

    二宮 崇

      More details

    Authorship:Principal investigator  Grant type:Competitive

    researchmap

  • 重要な特徴を自動的に発見する系列ラべリング学習の研究

    2010.4 - 2013.3

    日本学術振興会  科学研究費補助金 基盤研究(C) 

    二宮 崇

      More details

    Authorship:Principal investigator  Grant type:Competitive

    researchmap

  • リアルな能動学習による英語品詞解析の高精度化

    2010.4 - 2011.3

    愛媛大学  研究活性化事業 スタートアップ支援 

    二宮 崇

      More details

    Authorship:Principal investigator  Grant type:Competitive

    researchmap

  • A STUDY OF RESOLVING LONG TAIL PHENOMENA BY MACHINE LEARNING

    2009 - 2012

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research  Grant-in-Aid for Scientific Research (A)

    NAKAGAWA Hiroshi, YOSHIDA Minoru, KIYOTA Youji, SATO Issei, NINOMIYA Takashi

      More details

    Grant amount:\47060000 ( Direct Cost: \36200000 、 Indirect Cost:\10860000 )

    We developed a clustering system which makes clusters of web pages in response to a person name query in 2009 as planned, and evaluate it experimentally. In 2010, our contribution is a new non-negative probabilistic matrix decomposition algorithm and application of Variational Bayes method to Pitman-YO process. In 2011, our contribution for PPDM is a link analysis algorithm with public key encryption and specific protocol. In 2012, we developed a new online learning algorithm as well as new PPDM method.

    researchmap

  • 主辞駆動句構造文法のための統計同期文法による機械翻訳

    2007.4 - 2010.3

    日本学術振興会  科学研究費補助金 若手研究(A) 

    二宮 崇

      More details

    Authorship:Principal investigator  Grant type:Competitive

    researchmap

  • 多言語Webテキストからの知識マイニング関する研究

    2007 - 2008

    日本学術振興会  科学研究費助成事業  特定領域研究

    中川 裕志, 二宮 崇, 吉田 稔, 清田 陽司

      More details

    Grant amount:\10200000 ( Direct Cost: \10200000 )

    知識マイニングアルゴリズムの開発 : 多言語テキストコーパスから有用な情報抽出を行うための知識マイニングアルゴリズムとして、複数トピックを併せ持つテキストにおいてトピックを潜在変数とした単語の分類を行う統計的機械学習アルゴリズムを、階層的ディリクレ過程を基礎にした数理モデルによって開発した。これによってテキストにおける潜在トピックとそのトピックに対応する単語集合という知識を自動抽出できるアルゴリズムが明らかになった。
    人名の参照曖昧性解消 : Webテキスト処理において重要な応用である同性同名の人物の検索結果を実世界の異なる人物を記述するページごとにクラスタリングする参照曖昧性解消システムを開発した。これは、教師なし機械学習によるため、精度、高速性の両面から検討し、Web検索エンジンで人名検索を行った結果において同性同名の人物を参照するページを実世界において異なる人物毎に5秒程度で高速にクラスタリングするシステムの開発し、その精度の実験的評価を行った結果、F値で0.8を得た。
    スパムプログ分析 : Web上の重要な情報資源であるブログは常にスパムブログに悩まされており、排除のために大きなコストがかかっている。評判分析などの目的でブログの有効利用を図ることができる環境整備のツールとしてスパムブログの判定に役立つようなスパムブログの構造分析システムについて検討した。この結果、語彙にかかわる素性を分割してSVMを適用し、その結果をロジスティック回帰して組み合わせる方法によって、精度0.88を得た。

    researchmap

  • 多言語Webテキストからの知識マイニングに関する研究

    2006

    日本学術振興会  科学研究費助成事業  特定領域研究

    中川 裕志, 二宮 崇, 吉田 稔, 清田 陽司

      More details

    Grant amount:\5900000 ( Direct Cost: \5900000 )

    表記の研究テーマを推進するにあたっては,大量ないし多様なテキストを処理する必要がある.本年度は,このような目的に沿って,以下の基本的テキスト処理技術の探求,Webテキスト処理ツールの開発を行った.
    (1)大量のWebテキストから比較的軽い処理で知識の候補となるイベントを網羅的に抽出する半構造マイニングの手法を考案して,実装した.知識抽出にあたって、文の係り受け構造を,文節をラベルとする節点を保持する木構造で表したのでは,助詞や表記上のぶれにより,節点数の少ない部分木が抽出されてしまう.そこで係り受け構造を表現する新しいデータ構造を提案し,そのデータ構造に対するマイニング手法を提案することで,上記の問題を解決した.
    (2)将来必要となる精密な知識をテキストから抽出するためのインフラストラクチャーとなるHPSG文法による構文解析システムの研究を行った.従来のモデルに比べ,提案した極語彙化モデルはほぼ同じ精度を達成しながら,4〜5倍程度の高速化に成功している.もうひとつの提案である合成モデルでは,従来のモデルにくらべ3〜4倍程度の高速化を達成しつつ,適合率および再現率がおよそ2ポイント向上している.
    (3)HTMLで書かれたHTML文書であるが,その構造であるレイアウト情報を教師なし学習で自動的に抽出するシステムを検討した.
    (4)既存のサーチエンジンを越える使い勝手を実現するために,Webテキストと伝統的な情報の宝庫である図書館を連携させる目的で,Web上の百科事典Wikipediaを仲介とする方法を考案した.具体的にはWebの世界と図書館の世界をWikipediaを介してつなぐことによって,両者の世界の利点を生かした情報探索を実現するための試作システムを構築した.

    researchmap

  • A Study for Knowledge ExtractionAid System from Web Text

    2005 - 2007

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research  Grant-in-Aid for Scientific Research (A)

    NAKAGAWA Hiroshi, YONEZAWA Akinori, TAURA Kenjiro, NINOMIYA Takashi, YOSHIDA Minoru, KIYOTA Youji

      More details

    Grant amount:\43420000 ( Direct Cost: \33400000 、 Indirect Cost:\10020000 )

    We aimed at a system that extracts texts or part of texts including knowledge which various users are interested in from huge amount of Web pages in this research. We developed the following systems for this purpose.
    (1) A system which extracts terms that characterize a search engine result web pages using the term extraction system "Gensen Web" which we have already developed.
    (2) A system which extracts definition of terms which we extract by the system of (1) and relations among these terms. To accomplish this task, we utilize the usage consultation system via Web search engine called "Kiwi."
    (3) In order to make more efficient system of (2), we employed a suffix array technology and use the web pages crawled in advance. We named the system as "UT-Kiwi" and made it publically available from the Internet.
    (4) To enhance the above described systems, we developed a people name search engine named "Nayose." When we search pages for given people name, we get pages indicating distinct person even though they have the same name. Our system clusters those web pages according to the real person.
    (5) Aiming at more innovative knowledge extraction, we also studied new machine learning algorithms based on non-parametric Bayes theory.
    (6) Utilize web page in English more, we developed the Sakumon system which is an assisting system for English cloze test using English web pages.

    researchmap

  • 主辞駆動句構造文法に基づく並列処理を用いた頑健な自然言語処理の研究

    1998.4 - 2001.3

    日本学術振興会  特別研究員奨励費 

    二宮 崇

      More details

    Authorship:Principal investigator  Grant type:Competitive

    researchmap

▼display all

Teaching Experience (On-campus)

▼display all

Teaching Experience

  • Disaster Informatics

    2024.4 Institution:Ehime University

     More details

  • 人工知能概論B

    2023.12 Institution:愛媛大学 大学院理工学研究科

     More details

  • データサイエンス概論

    2023.4 Institution:愛媛大学 大学院理工学研究科

     More details

  • 人工知能概論A

    2023.4 Institution:愛媛大学 大学院理工学研究科

     More details

  • ICT/データサイエンス/AI特論

    2023.4 Institution:愛媛大学 地域レジリエンス学環

     More details

  • 時系列データ解析

    2021.10 Institution:愛媛大学 工学部 工学科

     More details

  • 機械学習Ⅲ

    2021.10 Institution:愛媛大学 工学部 工学科

     More details

  • 工学リテラシーⅢ

    2020.10 Institution:愛媛大学 工学部 工学科

     More details

  • コンピュータ工学入門

    2019.10 Institution:愛媛大学 工学部 工学科

     More details

  • 工学リテラシーⅡ

    2019.4 Institution:愛媛大学 工学部 工学科

     More details

  • 知識工学

    2014.4 Institution:愛媛大学 工学部 情報工学科

     More details

  • 数理言語情報論

     More details

  • 情報数学

     More details

  • 算法設計要論

     More details

  • プログラミング言語

     More details

  • インターンシップ

     More details

  • 海外短期留学

     More details

  • データ構造とアルゴリズム

     More details

  • 情報リテラシー入門

    Institution:愛媛大学

     More details

  • 技術英語プレゼンテーション

     More details

▼display all

Media Coverage

  • 発見!アドレナ人 「言葉を理解するコンピュータを作る!」 TV or radio program

    テレビ新広島  発見!アドレナ人  2024.7

     More details

  • [経済研究会]大洲・喜多3月例会 Newspaper, magazine

    愛媛新聞社  愛媛新聞朝刊  2019.3

     More details

    Author:Other 

    researchmap