Skip to main content

Hiroshi Kanayama


Staff Researcher, IBM Research - Tokyo, IBM Japan

Research Interests

Fundamental Technologies

  • Syntactic Parsing:
    Japanese dependency parser suitable for many applications
  • Semantic Processing:
    Extraction of "applicable" semantic structures such as favorable/unfavorable features embedded in people's opinion and relationships for question answering

Applications

Publications

Journal

  • Kanayama, H., Nasukawa, T.: "Unsupervised Lexicon Induction for Clause-level Detection of Evaluations", Journal of Natural Language Engineering, vol. 18, no. 1, pp. 83--107, 2011.
  • Kanayama, H., Nasukawa, T., and Watanabe, H.: "A Sentiment Analysis Method using Tree Transfer Model (in Japanese)", Transactions of the Japanese Society for Artificial Intelligence, vol. 26, no. 1, pp. 273--283, 2011.
  • Kanayama, H., Torisawa, K., Mitsuishi, Y., and Tsujii, J.: "A dependency parsing model which selects modifiees from at most three candidates (in Japanese)", Journal of Natural Language Processing, vol. 7, no. 5, pp. 71--91, 2000.

International Conferences

  • Tsuboi, Y., Kanayama, H., Ohno, M. and Unno, Y.: "Syntactic difference based approach for NTCIR-9 RITE task", In Proceedings of the 9th NTCIR Workshop Meeting on Evaluation of Information Access Technologies, pp. 401--411, December 2011.
  • Shima, H., Kanayama, H., Lee, C. W., Lin C. J., Mitamura, T., Miyao, Y., Shi, S., Takeda, K.: "Overview of NTCIR-9 RITE: Recognizing Inference in TExt", In Proceedings of the 9th NTCIR Workshop Meeting on Evaluation of Information Access Technologies, pp. 291--301, December 2011.
  • Kanayama, H. and Nasukawa T.: "Textual Demand Analysis: detection of users' wants and needs from opinions", In Proceedings of International Conference on Computational Linguistics (COLING), pp. 409--416, August 2008. [PDF]
  • Ikawa, Y and Kanayama H.: "A New Document Masking Approach for Removing Confidential Information", In Proceedings of IEEE Conference on Enterprise Computing, E-Commerce and E-Services (EEE), 2007.
  • Kanayama, H. and Nasukawa T.: "Fully Automatic Lexicon Expansion for Domain-oriented Sentiment Analysis" , In Proceedings of Empirical Methods in Natural Language Processing (EMNLP), pp. 355--363, July 2006. [PDF]
  • Kanayama, H., Nasukawa T. and Watanabe, H.: "Deeper Sentiment Analysis Using Machine Translation Technology,", In Proceedings of the 20th International Conference on Computational Linguistics (COLING 2004), August 2004. [PDF]
  • Kanayama, H. and Watanabe H.: "Multilingual Translation via Annotated Hub Language", Proc. of MT Summit IX, pp. 202--207, September 2003. [PDF]
  • Kanayama, H: "Paraphrasing Rules for Automatic Evaluation of Translation into Japanese", Proc. of IWP2003 - The Second International Workshop on Paraphrasing, pp. 88--93, July 2003. [PDF]
  • Kanayama, H: "An Iterative Algorithm for Translation Acquisition of Adpositions", Proc. of TMI 2002, pp. 85--95, March 2002. [PDF]
  • Kanayama, H., Torisawa, K., Mitsuishi, Y., and Tsujii, J.: "A Hybrid Japanese Parser with Hand-crafted Grammar and Statistics", Proc. of 18th COLING, pp. 411--417, August 2000. [PDF]
  • Kanayama, H., Torisawa, K., Mitsuishi, Y., and Tsujii, J.: "Statistical Dependency Analysis with an HPSG-based Japanese Grammar". In the Proceedings of the fifth Natural Language Processing Pacific Rim Symposium (NLPRS). pp. 138--143, November 1999.

Workshops and Domestic Conferences

  • Tsuboi, Y., Kanayama, H., Ohno, M. and Unno, Y.: "Syntactic difference based approach for NTCIR-9 RITE task", In Proceedings of the 9th NTCIR Workshop Meeting on Evaluation of Information Access Technologies, pp. 401--411, December 2011. [PDF]
  • Shima, H., Kanayama, H., Lee, C. W., Lin C. J., Mitamura, T., Miyao, Y., Shi, S., Takeda, K.: "Overview of NTCIR-9 RITE: Recognizing Inference in TExt", In Proceedings of the 9th NTCIR Workshop Meeting on Evaluation of Information Access Technologies, pp. 291--301, December 2011.

See Japanese page for domestic conference papers.

Talk, Lecture

  • Hiroshi Kanayama: "Why Watson Answered Questions on the TV Quiz Show?", special talk in the PRMU/DE Symposium, IEICE, 2011.
  • Hiroshi Kanayama and David Ferrucci: "Building Watson", invited talk in the 12th Spoken Language Symposium, 2010.
  • Hiroshi Kanayama: "Analysis of Sentiment and Demand", in the lecture series on text mining at Keio University, 2009 and 2010.
  • Hiroshi Kanayama: "ESPER: Extractor of Sentiment and Preference ExpRessions", LTI Seminar at Carnegie Mellon University. 18 April, 2008.

Back to top

Award, etc.

Award

  • Best Paper Award, 11th Annual Meeting of The Association for Natural Language Processing

Social Activities

  • Organizer member, SIG for Natural Language Understanding and Models of Communication, IEICE (2010-)
  • Task organizer of the RITE task in NTCIR-9, 2010-2011
  • PC member of EMNLP 2011
  • PC member of NAACL-HLT 2010
  • PC member of COLING 2010
  • Editorial Board Member for Journal of Natural Language Processing (2008-2010)
  • PC member of ACL-IJCNLP 2009
  • PC member of AIRS 2009
  • PC member of EMNLP 2009
  • Technical committee member, SIG for Natural Language Understanding and Models of Communication, IEICE (2005-2010)
  • PC member of EMNLP 2008
  • PC member of ACL-HLT 2008
  • PC member of EMNLP-CoNLL 2007

Back to top

Contact

IBM Research - Tokyo, IBM Japan
1623-14 Shimotsuruma, Yamato-shi, Kanagawa 242-8502 Japan
hkana AT jp DOT ibm DOT com

Back to top

Japanese Page

金山 博

Photo

Hiroshi Kanayama