Kentaro Torisawa

Director General,
Data-driven Intelligent System Research Center (DIRECT),
Universal Communication Research Institute (UCRI),
NICT

Research

I am supervising the Data-driven Intelligent System Research Center (DIRECT), NICT. In this research center, we conduct research on the following three topics.
  • Creating large-scale language resources, including various types of corpora and dictionaries, by applying NLP technologies and automatic knowledge acquisition methods to Web data. Of course, the development of the knowledge acquisition methods itself is an important research issue for us.
  • Development of Web services/applications that can behave intelligently by using language resources automatically acquired from the Web.
  • Development of basic tools in NLP, including morphological analyzers and parsers.
As the final goal, we aim to develop genuinely intelligent systems by leveraging the auto-generated language resources and knowledge, and analyzing the structure of knowledge hidden behind language, in the form of the huge body of text available on the Web. Our major research results in the last few years include the following two systems.
  • A concept dictionary: A large-scale semantic network created by automatic knowledge acquisition from the Web. It covers more than one million Japanese words.
  • The TORISHIKIKAI search support system: This search support system enables users to find unexpected but potentially valuable information, i.e. "unknown unknowns", from the Web.

We think these two systems can form the basis for intelligent Web services/applications and spoken dialog systems. In addition, we plan to make these resources available to researchers in universities and private companies.

Short Bio

I graduated from University of Tokyo in 1992 (BSc in computer science). After receiving MSc in Computer science from Graduate School of Science, University of Tokyo, I became a research associate in the same school in 1995. In 2001, I was appointed associate professor in School of Information Science, Japan Advanced Institute of Science and Technology. From 2008, I’m working at NICT and currently serving as the director general of the Data-Driven Intelligent Research Center.

Publications

  • Autonomic Resource Management for Program Orchestration in Large-scale Data Analysis, Masahiro Tanaka, Kenjiro Taura and Kentaro Torisawa, In the Proceedings of 31st IEEE International Parallel and Distributed Processing Symposium (IPDPS 2017), Orland, Florida, USA, May, 2017.(to appear)

  • Improving Event Causality Recognition with Multiple Background Knowledge Sources using Multi-Column Convolutional Neural Networks Canasai Kruengkrai, Kentaro Torisawa, Chikara Hashimoto, Julien Kloetzer, Jong-Hoon Oh and Masahiro Tanaka, In the Proceedings of the 31st AAAI Conference on Artificial Intelligence (AAAI-17), pp. 3466-3473, San Francisco, California, USA, Feb, 2017

  • Multi-column Convolutional Neural Networks with Causality-Attention for Why-Question Answering, Jong-Hoon Oh, Kentaro Torisawa, Canasai Kruengkrai, Ryu Iida and Julien Kloetzer, In the Proceedings of The tenth ACM International Conference on Web Search and Data Mining (WSDM2017), pp.415-424, Cambridge, UK, February, 2017. [WEB]

  • WISDOM X, DISAANA and D-SUMM: Large-scale NLP Systems for Analyzing Textual Big Data, Junta Mizuno, Masahiro Tanaka, Kiyonori Ohtake, Jong-Hoon Oh, Julien Kloetzer, Chikara Hashimoto and Kentaro Torisawa, In the Proceedings of the 26th International Conference on Computational Linguistics (COLING 2016) (Demo Track), pp.263-267, Osaka, Japan, December, 2016.

  • Intra-Sentential Subject Zero Anaphora Resolution using Multi-Column Convolutional Neural Network, Ryu Iida, Kentaro Torisawa, Jong-Hoon Oh, Canasai Kruengkrai and Julien Kloetzer, In the Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2016), Austin, Texas, USA, November, 2016.

  • Low Latency and Resource-aware Program Composition for Large-scale Data Analysis, Masahiro Tanaka, Kenjiro Taura and Kentaro Torisawa, In the Proceedings of the 16th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid 2016), pp.325--330, Cartagena, Colombia, USA, May, 2016.

  • A Semi-Supervised Learning Approach to Why-Question Answering, Jong-Hoon Oh, Kentaro Torisawa, Chikara Hashimoto, Ryu Iida, Masahiro Tanaka and Julien Kloetzer, In the Proceedings of the 30th AAAI Conference on Artificial Intelligence (AAAI-16), pp.3022--3029, Phoenix, USA, February, 2016.

  • Recognizing Complex Negation on Twitter, Junta Mizuno, Canasai Kruengkrai, Kiyonori Ohtake, Chikara Hashimoto, Kentaro Torisawa, Julien Kloetzer, In the Proceedings of the 29th Pacific Asia Conference on Language, Information and Computation, pp.544--552, Shanghai, China, October, 2015

  • Large-Scale Acquisition of Entailment Pattern Pairs by Exploiting Transitivity, Julien Kloetzer, Kentaro Torisawa, Chikara Hashimoto, Jong-Hoon Oh, In the Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2015), pp.1649--1655, Lisbon, Portugal, September, 2015

  • Intra-sentential Zero Anaphora Resolution using Subject Sharing Recognition, Ryu Iida, Kentaro Torisawa, Chikara Hashimoto, Jong-Hoon Oh, Julien Kloetzer, In the Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2015), pp.2179--2189, Lisbon, Portugal, September, 2015

  • Generating Event Causality Hypotheses through Semantic Relations, Chikara Hashimoto, Kentaro Torisawa, Julien Kloetzer and Jong-Hoon Oh, In the Proceedings of the 29th AAAI Conference on Artificial Intelligence (AAAI-15), pp.2396--2403, Austin, Texas, USA, January, 2015

  • Million-scale Derivation of Semantic Relations from a Manually Constructed Predicate Taxonomy, Motoki Sano, Kentaro Torisawa, Julien Kloetzer, Chikara Hashimoto, Istvan Varga and Jong-Hoon Oh, In the Proceedings of the 25th International Conference on Computational Linguistics (COLING 2014), pp.1423-1434, Dublin, Ireland, August, 2014.

  • Toward Future Scenario Generation: Extracting Event Causality Exploiting Semantic Relation, Context, and Association Features, Chikara Hashimoto, Kentaro Torisawa, Julien Kloetzer, Motoki Sano, Istvan Varga, Jong-Hoon Oh and Yutaka Kidawara, In the Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (ACL 2014), pp.987-997, Baltimore, Maryland, USA, June, 2014.

  • Two-stage Method for Large-scale Acquisition of Contradiction Pattern Pairs using Entailment, Julien Kloetzer, Stijn De Saeger, Kentaro Torisawa, Chikara Hashimoto, Jong-Hoon Oh, Kiyonori Ohtake, In the Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2013), pp.693-703, Seattle, USA, October, 2013.

  • NICT Disaster Information Analysis System, Kiyonori Ohtake, Jun Goto, Stijn De Saeger, Kentaro Torisawa, Junta Mizuno and Kentaro Inui, In Companion Volume of the Proceedings of The 6th International Joint Conference on Natural Language Processing (IJCNLP 2013) (Demo Track), pp.29-32, Nagoya, Japan, October, 2013.

  • WISDOM2013: A Large-scale Web Information Analysis System, Masahiro Tanaka, Stijn De Saeger, Kiyonori Ohtake, Chikara Hashimoto, Makoto Hijiya, Hideaki Fujii and Kentaro Torisawa, In Companion Volume of the Proceedings of The 6th International Joint Conference on Natural Language Processing (IJCNLP 2013) (Demo Track), pp.45-48, Nagoya, Japan, October, 2013.

  • Why-Question Answering using Intra- and Inter-Sentential Causal Relations, Jong-Hoon Oh, Kentaro Torisawa, Chikara Hashimoto, Motoki Sano, Stijn De Saeger, and Kiyonori Ohtake, In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (ACL 2013), pp.1733-1743, Sofia, Bulgaria, August, 2013.

  • Aid is Out There: Looking for Help from Tweets during a Large Scale Disaster, Istvan Varga, Motoki Sano, Kentaro Torisawa, Chikara Hashimoto, Kiyonori Ohtake, Takao Kawai, Jong-Hoon Oh and Stijn De Saeger, In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (ACL 2013), pp.1619-1629, Sofia, Bulgaria, August, 2013.

  • Minimally Supervised Method for Multilingual Paraphrase Extraction from Definition Sentences on the Web, Yulan Yan, Chikara Hashimoto, Kentaro Torisawa, Takao Kawai, Jun’ichi Kazama and Stijn De Saeger, In Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT2013), pp.63-73, Atlanta, USA, June, 2013.

  • Chinese Evaluative Information Analysis, Yiou Wang, Jun’ichi Kazama, Takuya Kawada, Kentaro Torisawa, In Proceedings of the 24th International Conference on Computational Linguistics (COLING 2012), pp.2773-2788, Mumbai, India, December, 2012.

  • Requests in tweets during a crisis: A systemic functional analysis of tweets on the Great East Japan Earthquake and the Fukushima Daiichi nuclear disaster, Motoki Sano, Istvan Varga, Jun'ichi Kazama and Kentaro Torisawa, In Proceedings of the 39th International Systemic Functional Congress, pp. 135-140, Sydney, Australia, July, 2012.

  • Excitatory or Inhibitory: A New Semantic Orientation Extracts Contradiction and Causality from the Web, Chikara Hashimoto, Kentaro Torisawa, Stijn De Saeger, Jong-Hoon Oh and Jun’ichi Kazama, In Proceedings of Conference on Empirical Methods in Natural Language Processing and Natural Language Learning (EMNLP-CoNLL 2012), pp.619-630, Jeju, Korea, July, 2012. supplementary materials

  • Why Question Answering using Sentiment Analysis and Word Classes, Jong-Hoon Oh, Kentaro Torisawa, Chikara Hashimoto, Takuya Kawada, Stijn De Saeger, Jun’ichi Kazama and Yiou Wang, In Proceedings of Conference on Empirical Methods in Natural Language Processing and Natural Language Learning (EMNLP-CoNLL 2012), pp.368-378, Jeju, Korea, July, 2012.
    supplementary materials

  • Bitext Dependency Parsing with Auto-generated Bilingual Treebank, Wenliang Chen, Jun’ichi Kazama, Min Zhang, Yoshimasa Tsuruoka, Yujie Zhang, Yiou Wang, Kentaro Torisawa and Haizhou Li, In IEEE Transaction on Audio, Speech and Language Processing, Vol.20(5), pp.1461-1472, 2012.

  • Toward Finding Semantic Relations not Written in a Single Sentence: An Inference Method using Auto-Discovered Rules, Masaaki Tsuchida, Kentaro Torisawa, Stijn De Saeger, Jong Hoon Oh, Jun'ichi Kazama, Chikara Hashimoto and Hayato Ohwada, In Proceedings of the 5th International Joint Conference on Natural Language Processing (IJCNLP 2011), pp.902-910, Chiang Mai, Thailand, November, 2011.

  • Improving Chinese Word Segmentation and POS Tagging with Semi-supervised Methods Using Large Auto-Analyzed Data, Yiou Wang, Jun'ichi Kazama, Yoshimasa Tsuruoka, Wenliang Chen, Yujie Zhang and Kentaro Torisawa, In Proceedings of the 5th International Joint Conference on Natural Language Processing (IJCNLP 2011), pp.309-317, Chiang Mai, Thailand, November, 2011.

  • Similarity Based Language Model Construction for Voice Activated Open-Domain Question Answering, Istvan Varga, Kiyonori Ohtake, Kentaro Torisawa, Stijn De Saeger, Teruhisa Misu, Shigeki Matsuda and Jun'ichi Kazama, In Proceedings of the 5th International Joint Conference on Natural Language Processing (IJCNLP 2011), pp.536-544, Chiang Mai, Thailand, November, 2011.

  • Extending WordNet with Hypernyms and Siblings Acquired from Wikipedia, Ichiro Yamada, Jong-Hoon Oh, Chikara Hashimoto, Kentaro Torisawa, Jun'ichi Kazama, Stijn De Saeger and Takuya Kawada, In Proceedings of the 5th International Joint Conference on Natural Language Processing (IJCNLP 2011), pp.874-882, Chiang Mai, Thailand, November, 2011.

  • Relation Acquisition using Word Classes and Partial Patterns, Stijn De Saeger, Kentaro Torisawa, Masaaki Tsuchida, Jun’ichi Kazama, Chikara Hashimoto, Ichiro Yamada, Jong-Hoon Oh, Istvan Varga, Yulan Yan, In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2011), pp.825-835, Edinburgh, U.K. July, 2011.

  • SMT Helps Bitext Dependency Parsing, Wenliang Chen, Jun'ichi Kazama, Min Zhang, Yoshimasa Tsuruoka, Yujie Zhang, Yiou Wang, Kentaro Torisawa and Haizhou Li, In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2011), pp.73-83, Edinburgh, U.K. July, 2011.

  • Extracting Paraphrases from Definition Sentences on the Web, Chikara Hashimoto, Kentaro Torisawa, Stijn De Sager, Jun'ichi Kazama and Sadao Kurohashi, In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL-HLT 2011), pp. 1087-1097, Portland, USA, June, 2011.

  • Extraction from the Web of Articles Describing Problems, Their Solutions, and Their Causes, Masaki MURATA, Hiroki TANJI, Kazuhide YAMAMOTO, Stijn DE SAEGER, Yasunori KAKIZAWA, and Kentaro TORISAWA, in IEICE Transactions on Information and Systems Vol.E94-D, No.3, pp.734-737, Mar. 2011[WEB]

  • Using the Maximum Entropy Method for Natural Language Processing: Category Estimation, Feature Extraction, and Error Correction, Masaki Murata, Kiyotaka Uchimoto, Masao Utiyama, Qing Ma, Ryo Nishimura, Yasuhiko Watanabe, Kouichi Doi, Kentaro Torisawa, in Cognitive Computation Volume 2, Issue 4 (2010), pp.272?279 [WEB]

  • Exploiting Subtrees in Auto-Parsed Data to Improve Dependency Parsing, Wenliang Chen, Jun'ichi Kazama, Kiyotaka Uchimoto, and Kentaro Torisawa, Computational Intelligence, Accepted for publication, 2010.

  • Using Various Features in Machine Learning to Obtain High Levels of Performance for Recognition of Japanese Notational Variants, Masahiro Kojima, Masaki Murata, Jun'ichi Kazama, Kow Kuroda, Atsushi Fujita, Eiji Aramaki, Masaaki Tsuchida, Yasuhiko Watanabe and Kentaro Torisawa,In Proceedings of The 24th Pacific Asia Conference on Language, Information and Compuation (PACLIC 24), pp.653-660, Sendai, Japan, 2010.

  • Generation of Summaries that Appropriately and Adequately Express the Contents of Original Documents Using Word-Association Knowledge, Kazuki Takigawa, Masaki Murata, Masaaki Tsuchida, Stijn De Saeger, Kazuhide Yamamoto and Kentaro Torisawa, In Proceedings of The 24th Pacific Asia Conference on Language, Information and Compuation (PACLIC 24), pp.693-700, Sendai, Japan, 2010.

  • Large Scale Similarity-based Relation Expansion, Masaaki Tsuchida, Stijn De Saeger, Kentaro Torisawa, Masaki Murata, Jun'ichi Kazama, Kow Kuroda and Hayato Ohwada, In Proceeedings of the 4th International Universal Communication Symposium (IUCS 2010), pp.140-147, Beijing, China, October, 2010.[WEB]

  • Generating Information-Rich Taxonomy from Wikipedia, Ichiro Yamada, Chikara Hashimoto, Jong-Hoon Oh, Kentaro Torisawa, Kow Kuroda, Stijn De Saeger, Masaaki Tsuchida and Jun'ichi Kazama, In Proceeedings of the 4th International Universal Communication Symposium (IUCS 2010), pp. 96-103, Beijing, China, October, 2010.[WEB]

  • A Look inside the Distributionally Similar Terms, Kow Kuroda, Jun’ichi Kazama, and Kentaro Torisawa, In Proceedings of the Second Workshop on NLP Challenges in the Information Explosion Era (NLPIX 2010), pp. 40-49, Beijing, China, August, 2010.

  • Co-STAR: A Co-training Style Algorithm for Hyponymy Relation Acquisition from Structured and Unstructured Text, Jong-Hoon Oh, Ichiro Yamada, Kentaro Torisawa and Stijn De Saeger, In Proceedings of the 23rd International Conference on Computational Linguistics (COLING 2010), pp.842-850, Beijing China, August, 2010.

  • Improving Graph-based Dependency Parsing with Decision History, Wenliang Chen, Jun'ichi Kazama, Yoshimasa Tsuruoka and Kentaro Torisawa, In Proceedings of the 23rd International Conference on Computational Linguistics (COLING 2010), pp.126-134, Beijing China, August, 2010.

  • Bitext Dependency Parsing with Bilingual Subtree Constraints, Wenlian Chen, Jun’ichi Kazama and Kentaro Torisawa, In Proc. of The 48th Annual Meeting of the Association for Computational Linguistics, (ACL 2010), pp21-29, Uppsala, Sweden, July, 2010.

  • A Bayesian Method for Robust Estimation of Distributional Simlarities, Jun’ichi Kazama, Stijn De Saeger, Kow Kuroda, Masaki Murata and Kentaro Torisawa, In Proc. of The 48th Annual Meeting of the Association for Computational Linguistics, (ACL 2010), pp247-256, Uppsala, Sweden, July, 2010.

  • Organizing the Web's Information Explosion to Discover Unknown Unknowns, Kentaro Torisawa, Stijn de Saeger, Jun'ichi Kazama, Asuka. Sumida, Daisuke Noguchi, Yasunari. Kakizawa, Masaki Murata, Kow Kuroda, and Ichiro Yamada, in New Generation Computing (Special Issue on Information Explosion), Vol. 28(3), pp.217-236, July, 2010. [WEB]

  • Using the ME Method for NLP: Category Estimation, Important Feature Extraction, and Error Correction, Masaki Murata, Kiyotaka Uchimoto, Masao Utiyama, Qing Ma, Ryo Nishimura, Yasuhiko Watanabe, Kouichi Doi, and Kentaro Torisawa, In Proceedings of The Seventh International Symposium on Neural Networks (ISNN 2010), Shanghai, China, June, 2010.

  • Adapting Chinese Word Segmentation for Machine Translation Based on Short Units, Yiou Wang, Kiyotaka Uchimoto, Jun’ichi Kazama, Canasai Kruengkrai and Kentaro Torisawa, in Proceedings of the Seventh International Conference on Language Resources and Evaluation (lrec 2010) pp.1758-1764, Valletta, Malta, May 2010.

  • Why Wikipedia needs to make friends with WordNet, Kow Kuroda, Kentaro Torisawa, in Proceedings of the 5th International Conference on the Global WordNet Association (GWC-2010), pp. 9-16, Munbai, India, January, 2010.

  • Joint Chinese Word Segmentation and POS Tagging Using an Error-Driven Word-Character Hybrid Model,Canasai Kruengkrai, Kiyotaka Uchimoto, Jun'ichi Kazama, Yiou Wang, Kentaro Torisawa and Hitoshi Isahara, In the IEICE Transactions on Information and Systems, Special Issue on “Natural Language Processing and Its Applications?E Vol.E92-D, No.12, pp.2298-2305, December, 2009. [WEB]

  • Large Scale Relation Acquisition using Class Dependent Patterns, Stijn De Saeger, Kentaro Torisawa, Jun'ichi Kazama, Kow Kuroda and Masaki Murata, in Proceedings of the IEEE International Conference on Data Mining (ICDM'09), pp.764-769, Miami, Florida, USA, December, 2009. [WEB]

  • A Web Service for Automatic Word Class Acquisition, Stijn De Saeger, Jun'ichi Kazama, Kentaro Torisawa, Masaki Murata, Ichiro Yamada, Kow Kuroda and Chikara Hashimoto, in Proceedings of the 3d International Universal Communication Symposium (IUCS'09), pp.132-138, Tokyo, Japan,December, 2009. [WEB]

  • When nouns need co-arguments: A case study of semantically unsaturated nouns, Kow Kuroda, Masaki Murata and Kentaro Torisawa, In Proceedings of the 5th International Conference on Generative Approaches to the Lexicon (GL2009), pp.2298-2305, Pisa, Italy, September, 2009.

  • Can Chinese Phonemes improve Machine Transliteration?: A Comparative Study of English-to-Chinese Transliteration models, Jong-Hoon Oh, Kiyotaka Uchimoto and Kentaro Torisawa, In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2009), pp.658-667, Singapore, August, 2009.

  • Hypernym Discovery based on Distributional Similarity and Hierarchical Structures, Ichiro Yamada, Kentaro Torisawa, Jun'ichi Kazama, Kow Kuroda, Masaki Murata, Stijn De Saeger, Francis Bond and Asuka Sumida, In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2009), pp.929-937, Singapore, August, 2009.

  • Improving Dependency Parsing with Subtrees From Auto-parsed Data, Wenliang Chen, Jun'ichi Kazama, Kiyotaka Uchimoto and Kentaro Torisawa, In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2009), pp.570-579, Singapore, August, 2009.

  • Large-scale Verb Entailment Acquisition from The Web, Chikara Hashimoto, Kentaro Torisawa, Kow Kuroda, Stijn De Saeger, Masaki Murata and Jun'ichi Kazama, In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2009), pp.1172-1181, Singapore, August, 2009.

  • Bilingual Co-Training for Monolingual Hyponymy-Relation Acquisition, Jong-Hoon Oh, Kiyotaka Uchimoto and Kentaro Torisawa, In Proceedings of the Joint conference of the 47th Annual Meeting of the Association for Computational Linguistics and the 4th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing (ACL-IJCNLP 2009), pp.432-440, Singapore, August, 2009.

  • An Error-Driven Word-Character Hybrid Model for Joint Chinese Word Segmentation and POS Tag, Canasai Kruengkrai, Kiyotaka Uchimoto, Jun'ichi Kazama, Yiou Wang, Kentaro Torisawa and Hitoshi Isahara, In Proceedings of the Joint conference of the 47th Annual Meeting of the Association for Computational Linguistics and the 4th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing (ACL-IJCNLP 2009), pp.513-521, Singapore, August, 2009.

  • Machine Transliteration with Target-Language Grapheme and Phoneme: Multi-Engine Transliteration Approach, Jong-Hoon Oh, Kiyotaka Uchimoto, and Kentaro Torisawa, In Proceedings of the ACL-IJCNLP 2009 Named Entities Workshop (NEWS 2009), pp.36-39, Singapore, August, 2009.

  • Multilingual Dependency Learning: Exploiting Rich Features for Tagging Syntactic and Semantic Dependencies, Hai Zhao, Wenliang Chen, Jun'ichi Kazama, Kiyotaka Uchimoto, and Kentaro Torisawa, In Proceedings of the Thirteenth Conference on Computational Natural Language Learning (CoNLL 2009) (Shared task Session), pp. 61-66, Boulder, CO, USA, June 2009.

  • Inducing Gazetteers for Named Entity Recognition by Large-scale Clustering of Dependency Relations, Jun'ichi Kazama and Kentaro Torisawa, In Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL-08: HLT), pp. 407-415, Columbus, Ohio, USA, June, 2008.

  • Enriching Multilingual Language Resources by Discovering Missing Cross-Language Links in Wikipedia, Jong-Hoon Oh, Daisuke Kawahara, Kiyotaka Uchimoto, Jun'ichi Kazama, and Kentaro Torisawa, In Proceedings of Web Intelligence (WI'08), Sydney, Australia, 2008. [WEB]

  • Looking for Trouble, Stijn De Saeger, Kentaro Torisawa, Jun'ichi Kazama, In Proceedings of The 22nd International Conference on Computational Linguistics (Coling2008), pp. 185-192, Manchester, UK, August, 2008.

  • Torishiki-kai, an Autogenerated Web Search Directory, Kentaro Torisawa, Stijn De Saeger, Yasunori Kakizawa Jun'ichi Kazama, Masaki Murata, Daisuke Noguchi, and Asuka Sumida, Proceedings of the Second International Symposium on Universal Communication (ISUC 2008), pp.179-186, Osaka, Japan, December, 2008.[WEB]

  • Boosting Precision and Recall of Hyponymy Relation Acquisition from Hierarchical Layouts in Wikipedia, Asuka Sumida, Naoki Yoshinaga and Kentaro Torisawa, In Proceedings of the sixth Language Resources and Evaluation Conference (LREC 2008), pp.2462-2469 Marrakech, Morocco, May., 2008.

  • Hacking Wikipedia for Hyponymy Relation Acquisition, Asuka Sumida and Kentaro Torisawa, In Proceedings of the Third International Joint Conference on Natural Language Processing (IJCNLP2008), pp.883-888, Hyderabad, India, Jan., 2008.

  • Analysis of the Degree of Importance of Information Using Newspapers and Questionnaires, Masaki Murata, Ryo Nishimura, Kouichi Doi, Toshiyuki Kanamaru and Kentaro Torisawa, Proceedings of 2008 IEEE International Conference on Natural Language Processing and Knowledge Engineering (IEEE NLP-KE'08), p.137-144, 2008.

  • Extraction and Visualization of Numerical and Named Entity Information from a Large Number of Documents, Masaki Murata, Masakazu Iwatate, Koji Ichii, Qing Ma, Tamotsu Shirado, Toshiyuki Kanamaru and Kentaro Torisawa, Proceedings of 2008 IEEE International Conference on Natural Language Processing and Knowledge Engineering (IEEE NLP-KE'08), 2008 [WEB]

  • A Discriminative Hybrid Model for Joint Chinese Word Segmentation and POS Tagging, Kruengkrai Canasai, Jun'ichi Kazama, Kiyotaka Uchimoto, Kentaro Torisawa, Hitoshi Isahara, In Proceedings of The 11th Oriental COCOSDA, 2008.

  • Open-Domain Attribute-Value Acquisition from Semi-Structured Texts, Naoki Yoshinaga and Kentaro Torisawa, In Proceedings of the Workshop on Ontolex 2007 -- The Lexicon/Ontology Interface held at the fifth International Semantic Web Conference, pp. 55-66, Busan, Republic of Korea, Nov., 2007.

  • Exploiting Wikipedia as External Knowledge for Named Entity Recognition, Jun'ichi Kazama and Kentaro Torisawa, Proceedings of EMNLP-CoNLL 2007, pp. 698-707, Prague, Czech Republic, June, 2007.

  • A New Perceptron Algorithm for Sequence Labeling with Non-local Features, Jun'ichi Kazama and Kentaro Torisawa, Proceedings of EMNLP-CoNLL 2007 (Poster) , pp. 315-324, Prague, Czech Republic, June, 2007.

  • A Novel Web-oriented Writing Environment using Objects' Facts Acquired from the Web, Naoki Yoshinaga, Kazumasa Nakamura, Kentaro Torisawa, In Proceedings of Web Intelligence 2007 Workshop on Intelligent Web Interaction, pp. 230-234, 2007.[WEB]

  • Concept-Instance Relation Extraction from Simple Noun Sequences Using a Search Engine on a Web Repository, Asuka Sumida, Kentaro Torisawa, Keiji Shinzato, Proceedings of the Web Content Mining with Human Language Technologies workshop on the fifth International Semantic Web Conference (ISWC2006), Athens, USA., November, 2006.

  • Constructing Dictionaries for Named Entity Recognition on Specific Domains from the Web, Keiji Shinzato, Satoshi Sekine, Naoki Yoshinaga, Kentaro Torisawa, Proceedings of the Web Content Mining with Human Language Technologies workshop on the fifth International Semantic Web Conference (ISWC2006), Athens, USA., November, 2006.

  • Semantic Role Recognition using Kernels on Weighted Marked Ordered Labeled Trees, Jun'ichi Kazama and Kentaro Torisawa, In Proceedings of the Tenth Conference on Computational Natural Language Learning (CoNLL-X), New York, USA., pp. 53-60, June, 2006.

  • Acquiring Inference Rules with Temporal Constraints by using Japanese Coordinated Sentences and Noun-Verb Co-occurrences, Kentaro Torisawa, In Proceedings of Human Language Technology Conference/North American chapter of the Association for Computational Linguistics annual meeting (HLT-NAACL06), New York, USA., pp. 57-64, June, 2006.

  • Finding Specification Pages According to Attributes, Naoki Yoshinaga and Kentaro Torisawa, In Proceedings of the 15th International World Wide Web Conference (WWW06), Edinburgh, UK., pp. 38-39, May, 2006.(poster)[WEB]

  • Speeding up Training with Tree Kernels for Node Relation Labeling, Jun'ichi Kazama and Kentaro Torisawa, In Proceedings of the Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing (HLT/EMNLP 2005), pp. 137-144, Vancouver, B.C., Canada, Oct., 2005.

  • A Simple WWW-based Method for Semantic Word Class Acquisition, Keiji Shinzato and Kentaro Torisawa, In Proceedings of the Recent Advances in Natural Language Processing (RANLP05), pp. 493-500, Borovets, Bulgaria, Sept., 2005.

  • Automatic Acquisition of Expressions Representing Preparation and Utilization of an Object, Kentaro Torisawa, In Proceedings of the Recent Advances in Natural Language Processing (RANLP05), pp. 556-560, Borovets, Bulgaria, Sept., 2005.

  • Automatic Discovery of Attribute Words from Web Documents, Kosuke Tokunaga, Jun'ichi Kazama and Kentaro Torisawa, In Proceedings of the Second International Joint Conference on Natural Language Processing (IJCNLP05), pp. 106-118, Jeju Island, Republic of Korea, Oct., 2005.

  • Extracting Hyponyms of Prespecified Hypernyms from Itemizations and Headings in Web Documents, Keiji Shinzato and Kentaro Torisawa, In Proceedings of the 20th International Conference on Computational Linguistics (COLING04), pp. 938-944, Geneva, Switzerland, Aug., 2004.

  • Parsing Comparison across Grammar Formalisms using Strongly Equivalent Grammars, Naoki Yoshinaga, Yusuke Miyao, Kentaro Torisawa, Jun’ichi Tsujii, Traitement Automatique des Langue, vol. 44(3), Special Issue on Evolutions in Parsing, pp.15-40, 2004.

  • Improving the Identification of Non-Anaphoric it using Support Vector Machines, Jose Carlos Clemente Litran, Kenji Satou and Kentaro Torisawa, International Joint Workshop on Natural Language Processing in Biomedicine and its Applications (NLPBA/BioNLP 2004)pp.58-61, Geneva, Switzerland, Aug., 2004 (poster).

  • Acquiring Hyponymy Relations from Web Documents, Keiji Shinzato and Kentaro Torisawa, In Proceedings of Human Language Technology Conference/North American chapter of the Association for Computational Linguistics annual meeting (HLT-NAACL04), pp. 73-80, Boston, U.S.A., May, 2004.

  • Extracting attributes and their values from Web pages, Minoru Yoshida, Kentaro Torisawa and Jun’ichi Tsujii, In A. Antonacopoulos and J. Hu(eds.): Web Document Analysis - Challenges and Opportunities, World Scientific - Series in Machine Perception and Artificial Intelligence, 2003.

  • An Unsupervised Learning Method for Commonsensical Inference Rules on Events, Kentaro Torisawa, in Proceedings of the Second CoLogNet-ElsNET Symposium, December, 2003.

  • Comparison between CFG filtering techniques for LTAG and HPSG, Naoki Yoshinaga, Kentaro Torisawa and Jun'ichi Tsujii, In the proceedings of the 41st ACL companion volume (ACL 2003), pp. 185-188, July 2003.

  • CFG Filtering and Parsing Strategies, Kentaro Torisawa, Kenji Nishida, Yusuke Miyao and Jun’ichi Tsujii, in Collaborative Language Engineering (Stephen Oepen et al., eds), CSLI Lecture Notes, 2002.[AMAZON]

  • Native-code Compilation of Feature Structures, Takaki Makino, Yusuke Miyao, Kentaro Torisawa, Yusuke Miyao and Jun’ichi Tsujii, in Collaborative Language Engineering (Stephen Oepen et al., eds), CSLI Lecture Notes, 2002.[AMAZON]

  • An Unsupervised Learning Method for Associative Relationships between Verb Phrases, Kentaro Torisawa, in Proceedings of of the 19th International Conference on Computational Linguistics (COLING 2002), pp. 1009-1015, Taipei, Taiwan, August, 2002.

  • A Nearly Unsupervised Learning Method for Automatic Paraphrasing of Japanese Noun Phrases, Kentaro Torisawa, in Proceedings of the Workshop on Automatic Paraphrasing, pp. 63-72, Tokyo, Japan, December, 2001.

  • An Unsuperveised Method for Canonicalization of Japanese Postpositions, Kentaro Torisawa, in Proceedings of the 6th Natural Language Processing Pacific Rim Symposium (NLPRS 2001), pp. 211-218, Tokyo, Japan, December, 2001.

  • A Method to Integrate Tables of the World Wide Web, Minoru Yoshida, Kentaro Torisawa and Jun'ichi Tsujii, in Proceedings of the International Workshop on Web Document Analysis (WDA 2001), Seattle, U.S., September, 2001.

  • Extracting ontologies from World Wide Web, Minoru Yoshida, Kentaro Torisawa and Jun'ichi Tsujii, in Proceedings of Pacific Association for Computational Linguistics 2001 (PACLING 2001), Kitakyushu, Japan, September, 2001.

  • Compiling an HPSG-based grammar into more than one CFG, Kenji Nishida, Kentaro Torisawa and Jun'ichi Tsujii, in Proceedings of Pacific Association for Computational Linguistics 2001 (PACLING 2001), Kitakyushu, Japan, September, 2001.

  • Efficient LTAG Parsing using HPSG parsers, Naoki Yoshinaga, Yusuke Miyao, Kentaro Torisawa and Jun'ichi Tsujii, in Proceedings of Pacific Association for Computational Linguistics 2001 (PACLING 2001), pp. 342-351, Kitakyushu, Japan, September, 2001.

  • Resource sharing among HPSG and LTAG communities by a method of grammar conversion from FB-LTAG to HPSG, Naoki Yoshinaga, Yusuke Miyao, Kentaro Torisawa and Jun'ichi Tsujii, in Proceedings of ACL/EACL Workshop on Sharing Tools and Resources for Research and Education, pp. 39-46, Toulouse, France, June, 2001.

  • An HPSG Parser with CFG Filtering, Kentaro Torisawa, Kenji Nishida, Yusuke Miyao, and Jun-ichi Tsujii, in Journal of Natural Language Engineering, Cambridge University Press, Vol 6(1), pp. 63--80, 2000.[WEB]

  • The LiLFeS abstract machine and its evaluation with the LinGO grammar, Yusuke Miyao, Takaki Makino, Kentaro Torisawa and Jun-ichi Tsujii, in Journal of Natural Language Engineering, Cambridge University Press, Vol 6(1), pp. 47--61, 2000.[WEB]

  • A Hybrid Japanese Parser with Hand-crafted Grammar and Statistics, Hiroshi Kanayama, Kentaro Torisawa, Yutaka Mitsuishi and Jun-ichi Tsujii, in Proceedings of the 18th International Conference on Computational Linguistics (COLING 2000), pp. 411-417, Saarbrucken, Germany, August, 2000.

  • Efficient FB-LTAG parser and its parallelization, Minoru Yoshida, Takashi Ninomiya, Kentaro Torisawa, Takaki Makino, and Jun-ichi Tsujii, in Proceedings of Pacific Association for Computational Linguistics '99 (PACLING'99), pp. 90--103, Waterloo, Canada, August, 1999.

  • Statistical Dependency Analysis with an HPSG-based Japanese Grammar, Hiroshi Kanayama, Kentaro Torisawa, Yutaka Mitsuisi and Jun-ichi Tsujii, in Proceedings of Natural Language Pacific Rim Symposium '99 (NLPRS'99), pp. 138--143, Beijin, China, November, 1999.

  • Efficient HPSG parsing algorithm with array unification, Kenji Nishida, Kentaro Torisawa and Jun-ichi Tsujii, in Proceedings of Natural Language Pacific Rim Symposium '99 (NLPRS'99), pp. 144--149, Beijin, China, November, 1999.[WEB]

  • Practical HPSG Parsers, Kentaro Torisawa, Takaki Makino, Takashi Ninomiya, Yutaka Mitsuisi, Yuka Tateishi, Kenji Nishida, Yusuke Miyao, Minoru Yoshida and Jun-ichi Tsujii, in The Proceedings of JSPS-HITACHI Workshop on New Challenges in Natural Language Processing and its Application, Saitama, Japan, pp. 100--105, May, 1998, Invited.

  • Packing of Feature Structures for Optimizing the HPSG-style Grammar translated from TAG, Yusuke Miyao, Kentaro Torisawa, Yuka Tateisi and Jun-ichi Tsujii, in Proceedings of Fouth International Workshop on Tree Adjoining Grammars and Related Frameworks (TAG+4), pp. 104--107, Philadelphia, U.S., August, 1998.

  • Translating the XTAG English Grammar to HPSG, Yuka Tateisi, Kentaro Torisawa, Yusuke Miyao and Jun-ichi Tsujii, in Proceedings of Fouth International Workshop on Tree Adjoining Grammars and Related Frameworks (TAG+4), pp. 172--175, Philadelphia, U.S., August, 1998.[WEB]

  • LiLFeS -- Towards Practical HPSG Parsers, Takaki Makino, Minoru Yoshida, Kentaro Torisawa and Jun-ich Tsujii, in Proceedings of the 17th International Conference on Conmupational Linguistics and the 36th Annual Meeting of the Association for Computational Linguistics (COLING-ACL'98), pp. 807--811, Montreal, Canada, August, 1998.

  • HPSG-Style Underspecified Japanese Grammar with Wide Coverage, Yutaka Mitsuisi, Kentaro Torisawa and Jun-ichi Tsujii, in Proceedings of the 17th International Conference on Computational Linguistics and the 36th Annual Meeting of the Association for Computational Linguistics (COLING-ACL'98), pp. 876--880, Montreal, Canada, August, 1998.

  • An Efficient Parallel Substrate for Typed Feature Structures on Shared Memory Parallel Machines, Takashi Ninomiya, Kentaro Torisawa and Jun-ichi Tsujii, in Proceedings of the 17th International Conference on Computational Linguistics and the 36th Annual Meeting of the Association for Computational Linguistics (COLING-ACL'98), pp. 968--974, Montreal, Canada, August, 1998.

  • A Parallel CKY Parsing Algorithm on Large-Scale Distributed-Memory Parallel Machines, Takashi Ninomiya, Kentaro Toriswa, Kenjiro Taura and Jun-ichi Tsujii, in Proceedings of the Pacific Association for Computational Linguistics '97 (PACLING'97), pp. 223--231, Tokyo, Japan, September, 1997.[WEB]

  • Extension of a feature structure abstract machine for partial unification, Kenji Nishida, Takaki Makino, Kentaro Torisawa, Yuka Tateisi, and Jun'ichi Tsujii, in Proceedings of the Pacific Association for Computational Linguistics '97 (PACLING'97), pp. 232--243, Tokyo, Japan, September, 1997.

  • LiLFeS - Practical Programming Language For Typed Feature Structures, Takaki Makino, Kentaro Torisawa and Jun-ichi Tsujii, in Proceedings of the Natural Language Processing Pacific Rim Symposium (NLPRS'97), pp. 239--244, Phuket, Thailand, September, 1997.

  • Computing Phrasal-signs in HPSG prior to Parsing, Kentaro Torisawa and Jun-ichi Tsujii, in Proceedigs of the 16th International Conference on Computational Linguistics (COLING'96), pp. 949--955, Copenhagen, Denmark, August, 1996.

  • Off-line Raising, Dependency Analysis and Partial Unification, Kentaro Torisawa and Jun-ichi Tsujii, in Proceedings of the Third International Conference on HPSG (HPSG 96), pp.14-23, Marseille, France, June, 1996.

  • Compiling HPSG-style grammar to Object-Oriented Language, Kentaro Torisawa and Jun-ichi Tsujii, in Proceedings of the Natural Language Processing Pacific Rim Symposium (NLPRS'95), pp. 568--573, Seoul, Korea, December, 1995. [WEB]

  • Automatic Acquisition of Content Words using an HPSG-based Parser, Keiko Horiguchi, Kentaro Torisawa and Jun-ichi Tsujii, in Proceedings of the Natural Language Processing Pacific Rim Symposium (NLPRS'95), pp. 320-325, Seoul, Korea, December, 1995.[WEB]

  • An HPSG-Parser for Automatic Knowledge Acquisition, Kentaro Torisawa and Jun-ichi Tsujii, in Proceedings of the 4th International Workshop on Parsing Technologies (IWPT95), pp. 250-251, Prague, Czech republic, September, 1995.