Japanese

INUI Kentaro

Courses

• Foundations of artificial intelligence
  
• Computational linguistics
• Natural language processing (at Kagoshima University)
  

Ongoing Research (publication list) 

1. Computational modeling of paraphrase
   We explore computational models for generating and recognizing paraphrases hoping to apply them to various text-based processing tasks including question answering, machine translation and multi-document summarization. We are currently engaged in an application-oriented project, called the Statement Map Project, which aims to develop a model which allows users to mine agreeing/conflicting statements for topics of interest from the Web.
   • Koji Murakami, Eric Nichols, Suguru Matsuyoshi, Asuka Sumida, Shouko Masuda, Kentaro Inui and Yuji Matsumoto. Statement Map: Assisting Information Credibility Analysis by Visualizing Arguments. Proceedings of the Second Workshop on Information Credibility on the Web (WICOW), 2009 (to appear) [PDF]
   • Atsushi Fujita, Kentaro Inui, Yuji Matsumoto. Exploiting Lexical Conceptual Structure for Paraphrase Generation. In Proceedings of Second International Joint Conference on Natural Language Processing (IJCNLP), pp.908-919, 2005. [PDF]
   • Tetsuro Takahashi, Kozo Nawata, Kentaro Inui and Yuji Matsumoto. Effects of structural matching and paraphrasing in question answering. IEICE Transactions on Information and Systems, Vol. E86-D, No. 9, pp. 1677-1685, 2003. [PDF]
2. Opinion and experience mining
   We propose a new UGC-oriented language technology application, called experience mining. Experience mining aims at automatically collecting instances of personal experiences as well as opinions from an explosive number of user generated contents (UGCs) such as weblog and forum posts and storing them in an experience database with semantically rich indices.
   • Kentaro Inui, Shuya Abe, Hiraku Morita, Megumi Eguchi, Asuka Sumida, Chitose Sao, Kazuo Hara, Koji Murakami, and Suguru Matsuyoshi, Experience Mining: Building a Large-Scale Database of Personal Experiences and Opinions from Web Documents, Proceedings of the 2008 IEEE/WIC/ACM International Conference on Web Intelligence, pp314-321, Dec. 2008 [PDF]
   • Nozomi Kobayashi, Kentaro Inui, and Yuji Matsumoto, Opinion Mining from Web Documents: Extraction and Structurization, Journal of the Japanese Society for Artificial Intelligence, vol.22, no.2, pp227-238, Mar. 2007 [PDF]
   • Demonstration system: "みんなの経験 (The Experiences of People)"
   • Japanese sentiment lexicon (in Japanese)
3. Semantic and discourse parsing
   Predicate-argument structure analysis, coreference resolution, rhetorical parsing, etc.
   • Ryu Iida, Kentaro Inui, and Yuji Matsumoto, Zero-Anaphora Resolution by Learning Rich Syntactic Pattern Features, ACM Transactions on Asian Language Information Processing (TALIP), vol.6, no.4, Dec. 2007 [PDF]
   • Ryu Iida, Mamoru Komachi, Kentaro Inui, and Yuji Matsumoto,Annotating a Japanese Text Corpus with Predicate-Argument and Coreference Relations, Proceedings of the Linguistic Annotation Workshop, pp.132-139, Jun. 2007 [PDF]
   • NAIST Text Corpus (in Japanese)
4. Commonsense knowledge acquisition from large corpora
   Text understanding ultimately requires commonsense knowledge. We are seeking a way to acquire knowledge about causal relations between events from large corpora.
   • Shuya Abe, Kentaro Inui, and Yuji Matsumoto, Two-phased event relation acquisition: coupling the relation-oriented and argument-oriented approaches, In Proceedings of the 22nd International Conference on Computational Linguistics (COLING-2008), pp1-8, Aug. 2008 [PDF]
   • Takashi Inui, Kentaro Inui, and Yuji Matsumoto. Acquiring causal knowledge from text using the connective marker tame. ACM Transactions on Asian Language Information Processing (TALIP), Vol. 4, Issue 4, pp.435-474, 2005. [PDF]
5. Computational Modeling of dialogue processing
   We are seeking computational frameworks that realize the interaction between language activities such as dialogues and other mental activities such as learning and emotionally-guided inference, and enhancing the competence of the existing goal-oriented dialogue systems.
   • Ryoko Tokuhisa, Kentaro Inui, and Yuji Matsumoto, Emotion classification using massive examples extracted from the Web, In Proceedings of the 22nd International Conference on Computational Linguistics (COLING-2008), pp881-888, Aug. 2008 [PDF]

Education

• Bachelor of Engineering in 1990, Department of Computer Science, Faculty of Engineering, Tokyo Institute of Technology
• Master of Engineering in 1992, Department of Computer Science, Graduate School of Information Science and Engineering, Tokyo Institute of Technology
• Doctor of Engineering in 1995, Department of Computer Science, Graduate School of Information Science and Engineering, Tokyo Institute of Technology 

Professional Career

• 1992-1995: Research Fellowship, Japan Society for the Promotion of Science (JSPS) 
• 1995-1998: Research Associate, Graduate School of Information Science and Engineering, Tokyo Institute of Technology
• 1998-2002: Associate Professor, Department of Artificial Intelligence, Kyushu Institute of Technology
  
• 1998-2001: Research Fellowship, PRESTO, Japan Science and Technology Corporation
• 2002-: Associate Professor, Graduate School of Information Science, Nara Institute of Science and Technology
  

Academic Awards

• COLING/ACL-2006 Best Asian NLP Paper Award: Exploiting syntactic patterns as clues in zero-anaphora resolution, 2006
• The Best Paper Award of the 10th Annual Meeting of the Association for Natural Language Processing:  A  Machine Learning-Based Method for Japanese NP-Anaphora Resolution, 2004
• The Best Paper Award of the 9th Annual Meeting of the Association for Natural Language Processing: Acquiring Causal Relation Knowledge from Text Corpora Using Connective Marker "tame", 2003
  
• Outstanding Paper Award: Two Complementary Case Studies for Emotion Tagging in Text Corpora, SIG-SLUD, Japanese Society for Artificial Intelligence, 2001
• Annual Best Paper Award of the Japanese Society for Artificial Intelligence: A Framework of Decision-Theoretic Utterance Planning, 1998
• The Best Paper Award of the 2nd Annual Meeting of the Association for Natural Language Processing: Probabilistic Partial Parsing, 1998
• The Best Paper Award of the 2nd Annual Meeting of the Association for Natural Language Processing: Selective Sampling for Word Sense Disambiguation, 1996
  

Social Activites