NAOYA INOUE/井之上 直也




Assistant Professor at Tohoku University (CS lab led by Kentaro Inui)
(2015/08/01--Present)
Visiting Academics at UCL Machine Reading Group (Host: Sebastian Riedel)
(2017/04/10--2017/09/29)

Address:
Communication Science Laboratory
6-6-05 Aramaki Aza Aoba, Aobaku, Sendai, Miyagi 980-8579, Japan

Telephone: +81-22-795-7091
Fax: +81-22-795-4285
Email: naoya-i aaaaaaattt ecei.tohoku.ac.jp
Twitter: @naoya_in

Welcome to my web site! I am an assistant professor at Tohoku University, Sendai, Japan. My research interest is in natural language processing, especially in AI-oriented discourse processing and language grounding problems. Currently I'm working on developing the framework of abductive discourse interpretation using large-scale commonsense knowledge resources. My CV is here.

Grants

Publications

  • International conferences/workshops
    1. Daiqin, Naoya Inoue, Paul Reisert and Kentaro Inui. Leveraging Document-specific Information for Identifying Relations in Scientific Articles. To appear in Proceedings of First International Workshop on SCIentific DOCument Analysis (SCIDOCA), November 2017. paper
    2. Reina Akama, Kazuaki Inada, Naoya Inoue, Sosuke Kobayashi and Kentaro Inui. Generating Stylistically Consistent Dialog Responses with Transfer Learning. To appear in Proceedings of the 8th International Joint Conference on Natural Language Processing (IJCNLP), November 2017. paper
    3. Shota Sasaki, Sho Takase, Naoya Inoue, Naoaki Okazaki and Kentaro Inui. Handling Multiword Expressions in Causality Estimation. In Proceedings of 12th International Conference on Computational Semantics (IWCS), September 2017. paper implementation
    4. Naoya Inoue and Andrew S. Gordon. A Scalable Weighted Max-SAT Implementation of Propositional Etcetera Abduction. In Proceedings of the 30th International Florida Artificial Intelligence Research Society Conference (FLAIRS), pp.62-67, May 2017. paper slides
    5. Melissa Roemmele, Sosuke Kobayashi, Naoya Inoue and Andrew Gordon. An RNN-based Binary Classifier for the Story Cloze Test. In Proceedings of the 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-level Semantics (LSDSem; EACL Workshop), pp.74-80, April 2017. paper
    6. Naoya Inoue, Yuichiro Matsubayashi, Masayuki Ono, Naoaki Okazaki and Kentaro Inui. Modeling Context-sensitive Selectional Preference with Distributed Representations. In Proceedings of the 26th International Conference on Computational Linguistics (COLING), pp.2829–2838, December 2016. paper poster
    7. Paul Reisert, Naoya Inoue, Naoaki Okazaki, and Kentaro Inui. Towards Recognizing Logic in Argumentative Texts (Extended Abstract). First International Workshop on SCIentific DOCument Analysis (SCIDOCA), November 2016.
    8. Naoya Inoue, Yasutaka Kuriya, Sosuke Kobayashi and Kentaro Inui. Recognizing potential traffic risks through logic-based deep scene understanding. In Proceedings of the 22nd ITS World Congress (ITSWC), October 2015. paper (draft) slides
    9. Paul Reisert, Naoya Inoue, Naoaki Okazaki and Kentaro Inui. A Computational Approach for Generating Toulmin Model Argumentation. In Proceedings of the 2nd Workshop on Argumentation Mining, pp.45–55, June 2015. paper
    10. Canasai Kruengkrai, Naoya Inoue, Jun Sugiura, and Kentaro Inui. An Example-Based Approach to Difficult Pronoun Resolution. In Proceedings of the 28th Pacific Asia Conference on Language, Information and Computing (PACLIC), pp.358-367, December 2014. paper
    11. Jun Sugiura, Naoya Inoue and Kentaro Inui. Recognizing Implicit Discourse Relations through Abductive Reasoning with Large-scale Lexical Knowledge. In Proceedings of the 1st Workshop on Natural Language Processing and Automated Reasoning (NLPAR), September 2013. paper
    12. Kazeto Yamamoto, Naoya Inoue, Yotaro Watanabe, Naoaki Okazaki and Kentaro Inui. Discriminative Learning of First-order Weighted Abduction from Partial Discourse Explanations. In Proceedings of the 14th International Conference on Intelligent Text Processing and Computational Linguistics (CICLING), pp.545-558, March 2013. paper
    13. Naoya Inoue, Ekaterina Ovchinnikova, Kentaro Inui, and Jerry R. Hobbs. Coreference Resolution with ILP-based Weighted Abduction. In Proceedings of the 24th International Conference on Computational Linguistics (COLING), pp.1291-1308, December 2012. paper slides
    14. Naoya Inoue and Kentaro Inui. Large-scale Cost-based Abduction in Full-fledged First-order Predicate Logic with Cutting Plane Inference. In Proceedings of the 13th European Conference on Logics in Artificial Intelligence (JELIA), pp.281-293, September 2012. paper slides
    15. Naoya Inoue and Kentaro Inui. ILP-based Reasoning for Weighted Abduction. In Proceedings of AAAI Workshop on Plan, Activity and Intent Recognition (PAIR), pp. 25-32, August 2011. paper slides
    16. Naoya Inoue, Ryu Iida, Kentaro Inui, and Yuji Matsumoto. Resolving Direct and Indirect Anaphora for Japanese Definite Noun Phrases. In Proceedings of the Conference of the Pacific Association for Computational Linguistics (PACLING), pp.268-273, September 2009. paper slides
  • Book chapter
    1. 井之上 直也(分担). 自然言語を中心とする記号処理, 独立行政法人情報処理推進機構 AI白書編集委員会, AI白書 2017, 1.4章, AI白書 2017, 株式会社角川アスキー総合研究所発行, 2017年7月. info
    2. Ryu Iida, Mamoru Komachi, Naoya Inoue, Kentaro Inui and Yuji Matsumoto. NAIST Text Corpus: Annotating Predicate-Argument and Coreference Relations in Japanese. In Nancy Ide and James Pustejovsky (Eds), Handbook of Linguistic Annotation, Part II, pp.1177-1196, Springer, July 2017. info
    3. Naoya Inoue, Ekaterina Ovchinnikova, Kentaro Inui, and Jerry R. Hobbs. Weighted Abduction for Discourse Processing Based on Integer Linear Programming. In Gita Sukthankar, Christopher Geib, Robert P. Goldman, Hung Bui, and David V. Pynadath (Eds), Plan, Activity, and Intent Recognition, Chapter 2, pp.33-55, Elsevier, March 2014. info
  • Journal papers
    1. Paul Reisert, Naoya Inoue, Naoaki Okazaki and Kentaro Inui. Designing a Task for Recognizing Argumentation Logic in Argumentative Texts. International Journal of Computational Linguistics and Applications, to appear, 2017.
    2. Paul Reisert, Naoya Inoue, Naoaki Okazaki and Kentaro Inui. Identifying and Ranking Relevant Claims for Decision Support. International Journal of Computational Linguistics and Applications, to appear, 2017.
    3. Ryo Takahashi, Naoya Inoue, Yasutaka Kuriya, Sosuke Kobayashi, and Kentaro Inui. Explaining potential risks in traffic scenes by combining logical inference and physics simulation. International Journal of Machine Learning and Computing, Vol. 6, No. 5, pp. 248-255, October 2016. paper
    4. 山本風人, 井之上直也, 乾健太郎. 機能的なリテラルを含む公理体系における仮説推論の効率化. 自然言語処理 Vol.23, No.3, pp.267-298, June 2016. paper
    5. Kazeto Yamamoto, Naoya Inoue, Kentaro Inui, Yuki Arase and Jun'ichi Tsujii. Boosting the Efficiency of First-order Abductive Reasoning Using Pre-estimated Relatedness between Predicates. International Journal of Machine Learning and Computing, Vol. 5, No. 2, pp. 114-120, April 2015. paper
    6. Naoya Inoue and Kentaro Inui. ILP-based Inference for Cost-based Abduction on First-order Predicate Logic. Journal of Natural Language Processing, Vol.20, No.5, pp.629-656, December 2013. paper
    7. 飯田龍, 小町守, 井之上直也, 乾健太郎, 松本裕治. 述語項構造と照応関係のアノテーション: NAISTテキストコーパス構築の経験から. 自然言語処理, Vol.17, No.2, pp.25-50, April 2010. (言語処理学会 20周年記念論文賞) paper
    8. Naoya Inoue, Ryu Iida, Kentaro Inui, and Yuji Matsumoto. Resolving Direct and Indirect Anaphora for Japanese Definite Noun Phrases. Journal of Natural Language Processing, Vol.17, No.1, pp.221-246, January 2010. paper
  • Domestic conferences
    1. 佐々木翔大, 高瀬翔, 井之上直也, 岡崎直観, 乾健太郎. 複単語表現を利用した因果関係推定モデルの改善. 情報処理学会研究報告. 自然言語処理研究会報告, Vol.2017-SLP-116 (22), pp.1-6, May 2017.
    2. Paul Reisert, Naoya Inoue, Naoaki Okazaki, Kentaro Inui. Deep Argumentative Structure Analysis as an Explanation to Argumentative Relations. 言語処理学会第23回年次大会論文集, pp.38-41, March 2017.
    3. 佐々木翔大, 高瀬翔, 井之上直也, 岡崎直観, 乾健太郎. 分散表現を用いた因果関係のモデル化. NLP若手の会 第11回シンポジウム, August 2016.
    4. 高橋諒, 井之上直也, 栗谷康隆, 山本風人, 乾健太郎. 交通オントロジと説明生成に基づく交通危険予測. 人工知能学会全国大会 (第30回) 論文集, June 2016.
    5. 佐藤祥多, 井之上直也, 乾健太郎, 樋口佐和, 渡部生聖. 因果関係に基づく雑談対話発話生成の試み. 人工知能学会全国大会 (第30回) 論文集, June 2016.
    6. 井之上直也, 岡崎直観, 乾健太郎. 感情状態に基づく因果関係推論の一般化. 言語処理学会第22回年次大会論文集, pp.889-892, March 2016. paper (draft) slides
    7. 大野雅之, 井之上直也, 松林優一郎, 岡崎直観, 乾健太郎. 分散表現による文脈情報を用いた選択選好モデル. 言語処理学会第22回年次大会論文集, pp.885-888, March 2016. (最優秀賞)
    8. 大野雅之, 井之上直也, 松林優一郎, 岡崎直観, 乾健太郎. 分散表現に基づく選択選好モデルの文脈化. 情報処理学会研究報告. 自然言語処理研究会報告, Vol.2016-NL-225, No.1, pp.1-9, January 2016. (優秀研究賞)
    9. Paul Reisert, Naoya Inoue, Naoaki Okazaki, Kentaro Inui. Determining Argument Strength and Consistency using a Causality-based Knowledge Graph. 第10回NLP若手の会 シンポジウム, September 2015.
    10. 小林颯介,井之上直也,栗谷康隆,近藤敏之,安部克則,奥野英一,乾健太郎. 物理モデルと論理推論の統合による運転シーンの潜在的危険の予測. 自動車技術会 2015年春季大会学術講演会講演予稿集, pp.1076-1081, May 2015.
    11. 山本風人, 井之上直也, 乾健太郎. 言語処理のための仮説推論エンジン Phillip. 言語処理学会第21回年次大会論文集, pp.377-380, March 2015.
    12. Computationalizing a Toulmin Model for Argumentation Generation. Paul Reisert, Naoya Inoue, Kentaro Inui, Toshihiko Yanase, Kohsuke Yanai. 言語処理学会第21回年次大会論文集, pp.828-831, March 2015.
    13. 井之上直也, 杉浦純, Canasai Kruengkrai, 乾健太郎. 共参照解析のための事象間関係知識の一般化に向けて. NLP若手の会 第9回シンポジウム, September 2014. poster
    14. 山本 風人,井之上 直也, 乾 健太郎, 荒瀬 由紀, 辻井 潤一. A*探索に基づく仮説推論の効率化. 情報処理学会研究報告, Vol.2014-NL-217, July 2014.
    15. 井之上直也, 杉浦純, 乾健太郎. 共参照解析のための事象間関係知識の文脈化. 言語処理学会第20回年次大会論文集, pp.717-720, March 2014. paper (draft) slides (最優秀賞)
    16. 杉浦純, 井之上直也, 乾健太郎. 共参照解析における事象間関係知識の適用. 言語処理学会第20回年次大会論文集, pp.713-716, March 2014.
    17. 稲田和明, 松林優一郎, 井之上直也, 乾健太郎. 効率的な推論処理のための日本語文の論理式変換に向けて. 言語処理学会第18回年次大会論文集, March 2013.
    18. Daiqin, Naoya Inoue, Kentaro Inui and Naoaki Okazaki. Acquisition of Inference Rules for Distinct Relative Entities. The 8th Symposium on Young Researcher Association for NLP Studies, September 2013.
    19. Naoya Inoue, Kazeto Yamamoto, Yotaro Watanabe, Naoaki Okazaki and Kentaro Inui. Online Large-margin Weight Learning for First-order Logic-based Abduction. In Proceedings of the 15th Information-Based Induction Sciences Workshop, pp.143-150, November 2012. paper (draft) poster (Honorable Mention)
    20. Naoya Inoue and Kentaro Inui. Extending ILP-based Abductive Inference with Cutting Plane Inference. In IPSJ SIG Technical Reports, Vol. 2012-NL-208 (5), pp.1-8, September 2012. slides
    21. 杉浦純, 井之上直也, 乾健太郎. 談話関係認識への連想情報の応用. NLP若手の会 第7回シンポジウム, September 2012.
    22. 山本風人, 井之上直也, 渡邊陽太郎, 岡崎直観, 乾健太郎. 重み付き仮説推論における部分的な正解仮説からの識別学習. NLP若手の会 第7回シンポジウム, September 2012. (奨励賞)
    23. 山本風人, 井之上直也, 渡邊陽太郎, 岡崎直観, 乾健太郎. 誤差逆伝播を利用した重み付き仮説推論の教師あり学習. 情報処理学会研究報告, Vol.2012-NL-206, May 2012. (学生奨励賞)
    24. 井之上直也, 乾健太郎, Ekaterina Ovchinnikova, Jerry R. Hobbs. 大規模世界知識を用いた仮説推論による談話解析の課題と対策. 言語処理学会第18回年次大会論文集, pp.119-122, March 2012. paper (draft) slides (優秀賞)
    25. 杉浦純, 井之上直也, 乾健太郎. 説明生成に基づく談話構造解析の課題分析. 言語処理学会第18回年次大会論文集, pp.115-118, March 2012.
    26. Kentaro Inui and Naoya Inoue. Scalable Abduction for Deep NLP. Workshop 'Perspectives on Processing Japanese', October 2011.
    27. 杉浦純, 井之上直也, 乾健太郎. 大規模語彙知識を用いた仮説推論による文章理解モデルの構築に向けて. NLP若手の会 第6回シンポジウム, September 2011. (優秀発表賞)
    28. Naoya Inoue and Kentaro Inui. An ILP Formulation of Abductive Inference for Discourse Interpretation. In IPSJ SIG Technical Reports, Vol. 2011-NL-203 (3), pp.1-13, September 2011. slides (山下記念研究賞)
    29. Naoya Inoue and Kentaro Inui. Toward Plan Recognition in Discourse Using Large-Scale Lexical Resources. 言語処理学会第17回年次大会発表論文集, pp. 928-931, March 2011. paper slides
    30. 井之上直也, 乾健太郎. 文章に潜在する書き手の心的状態推定に向けて. 自然言語処理若手の会第5回シンポジウム, September 2010. poster
    31. 井之上直也, 飯田龍, 乾健太郎, 松本裕治. 日本語文章における直接照応および間接照応の統合的解析. 情報処理学会第72回全国大会講演論文集, pp.2-541-542, March 2010. paper (draft)
    32. 井之上直也, 飯田龍, 乾健太郎, 松本裕治. 指定指示・代行指示を区別した指示連体詞の照応解析. 言語処理学会第15回年次大会発表論文集, pp.372-375, March 2009. paper (draft) slides
    33. 井之上直也, 江口萌, 有木隼人. wrica -ブログパーツで繋がる相互添削ネットワーク-. 自然言語処理学会若手の会第3回シンポジウム, September 2008. poster
  • Invited Talks
    1. 井之上直也. 説明生成に基づく交通シーンの危険予測. 自動車技術会第14回エレクトロニクス部門委員会, February 2016.
  • Miscellaneous
    1. 井之上直也, 乾健太郎. 書き手の問題解決プランの推定手法の検討. 自然言語処理合同研究会2010, November 2010. poster
    2. NAIST Creative and International Competitiveness Project (CICP2008)
      "Dear Proofreader(拝啓 添削者様) - Construction of a correction network with blog plugin -" poster presented in NAIST Science Festival 2009. poster

Software

Thesis

Awards

Other Interests

Contact Information

Naoya Inoue / @naoya_in / naoya-i aaattt ecei.tohoku.ac.jp
Communication Science Laboratory
Graduate School of Information Sciences
Tohoku University

$ Modified: 10/31/17 21:39:23 $