An integrated machine learning system that allows visual and interactive semi-automated error analysis specialized in natural language processing

• Project/Area Number: 21500130
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Single-year Grants
• Section: 一般
• Research Field: Intelligent informatics
• Research Institution: National Institute of Informatics (2011-2012); The University of Tokyo (2009-2010)
• Principal Investigator: KANO Yoshinobu 国立情報学研究所, 情報社会相関研究系, 外来研究員 (20506729)
• Co-Investigator(Kenkyū-buntansha): MIWA Makoto 東京大学, 大学院・情報学環, 特任研究員 (00529646)
• Project Period (FY): 2009 – 2012
• Project Status: Completed (Fiscal Year 2012)
• Budget Amount: ¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000); Fiscal Year 2011: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000); Fiscal Year 2010: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000); Fiscal Year 2009: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
• Keywords: 自然言語処理 / 機械学習 / エラー解析 / 視覚化 / 相互運用性 / 祖覚化

Research Abstract

Supervised machine learning methods are very often used in research and development of natural language processing technologies. We have designed and developed prototypical features that allow users to exploit the machine learning methods more easily and effectively, supporting automation and result analysis. We have applied these features to text mining from English biomedical literatures, obtaining user feedbacks for potential future works

Research Products

• [Journal Article] Jari Bjorne, Filip Ginter, Tapio Salakoski, Ekaterina Buyko, Udo Hahn, K Bretonnel Cohen, Karin Verspoor, Christophe Roeder, Lawrence E Hunter, Halil Kilicoglu, Sabine Bergler, Sofie Van Landeghem, Thomas Van Parys, Yves Van de Peer, Makoto Miwa, Sophia Ananiadou, Mariana Neves, Alberto Pascual-Montano, Arzucan Ozgur (2011)
  • Author(s): Yoshinobu Kano
  • Journal Title: Dragomir R Radev, Sebastian Riedel, Rune Saetre, Hong-Woo Chun, Jin-Dong Kim, Sampo Pyysalo, Tomoko Ohta and Jun'ichi Tsujii: "U-Compare bio-event meta-service: compatible BioNLP event extraction services" BMC Bioinformatics Volume: 12 Issue: 1 Pages: 481-481
  • DOI: 10.1186/1471-2105-12-481
  • Peer Reviewed
• [Journal Article] " Extracting bio-molecular events from literature - the BioNLP'09 shared task" (2011)
  • Author(s): Jin-Dong Kim, Tomoko Ohta, Sampo Pyysalo, Yoshinobu Kano and Jun'ichi Tsujii
  • Journal Title: Computational Intelligence Volume: 27(4) Issue: 4 Pages: 513-540
  • DOI: 10.1111/j.1467-8640.2011.00398.x
• [Journal Article] " U-Compare: a modular NLP workflow construction and evaluation system" (2011)
  • Author(s): Yoshinobu Kano, Makoto Miwa, Kevin Cohen, Larry Hunter, Sophia Ananiadou and Jun'ichi Tsujii
  • Journal Title: IBM Journal of Research and Development Volume: 55(3) Issue: 3 Pages: 11:1-11:10
  • DOI: 10.1147/jrd.2011.2105691
• [Journal Article] Extracting bio-molecular events from literature - the BioNLP’09 shared task (2011)
  • Author(s): Jin-Dong Kim, Tomoko Ohta, Sampo Pyysalo, Yoshinobu Kano, Jun'ichi Tsujii
  • Journal Title: Computational Intelligence Volume: 27(4) Pages: 513-540
  • Peer Reviewed
• [Journal Article] U-Compare: a modular NLP workflow construction and evaluation system (2011)
  • Author(s): Yoshinobu Kano, et al.
  • Journal Title: IBM Journal of Research and Development Volume: 55(3) Pages: 325-334
  • Peer Reviewed
• [Journal Article] "Text mining meets workflow : linking U-Compare with Taverna" (2010)
  • Author(s): Yoshinobu Kano, Paul Dobson, Mio Nakanishi, Jun'ichi Tsujii and Sophia Ananiadou
  • Journal Title: Bioinformatics, Oxford Journals Volume: 26(19) Issue: 19 Pages: 2486-2487
  • DOI: 10.1093/bioinformatics/btq464
• [Journal Article] "Extracting Protein-Interactions from Text with the Unified AkaneRE Event Extraction System" (2010)
  • Author(s): Rune Saetre, Kazuhiro Yoshida, Makoto Miwa, Takuya Matsuzaki, Yoshinobu Kano and Junichi Tsujii
  • Journal Title: Transactions on Computational Biology and Bioinformatics (TCBB) Volume: 7(3) Issue: 3 Pages: 442-453
  • DOI: 10.1109/tcbb.2010.46
• [Journal Article] Text Mining Meets Workflow : Linking U-Compare with Taverna (2010)
  • Author(s): Kano, Yoshinobu, Paul Dobson, Mio Nakanishi, Jun'ichi Tsujii, Sophia Ananiadou
  • Journal Title: Bioinformatics, Oxford Journals Volume: 26(19) Pages: 2486-2487
  • Peer Reviewed
• [Journal Article] Extracting Protein-Interactions from Text with the Unified AkaneRE Event Extraction System (2010)
  • Author(s): Swtre, Rune, Kazuhiro Yoshida, Makoto Miwa, Takuya Matsuzaki, Yoshinobu Kano, Junichi Tsujii
  • Journal Title: Transactions on Computational Biology and Bioinformatics (TCBB) Volume: 7(3) Pages: 442-453
  • Peer Reviewed
• [Journal Article] "U-Compare : share and compare text mining tools with UIMA" (2009)
  • Author(s): Yoshinobu Kano, William A. Baumgartner Jr, Luke McCrohon, Sophia Ananiadou, K. Bretonnel Cohen, Lawrence Hunter and Jun'ichi Tsujii:
  • Journal Title: Bioinformatics Volume: 25(15) Issue: 15 Pages: 1997-1998
  • DOI: 10.1093/bioinformatics/btp289
• [Journal Article] U-Compare : share and compare text mining tools with UIMA (2009)
  • Author(s): Kano, Yoshinobu, William A.Baumgartner Jr, Luke McCrohon, Sophia Ananiadou, K.Bretonnel Cohen, Lawrence Hunter, Jun'ichi Tsujii
  • Journal Title: Bioinformatics 25(15) Pages: 1997-1998
  • Peer Reviewed
• [Presentation] "BCCWJと関連ツールの相互運用"『現代日本語書き言葉均衡コーパス』 (2011)
  • Author(s): 狩野芳伸, 橋田浩一
  • Organizer: 完成記念講演会(招待講演)
  • Place of Presentation: JA共済ビルカンファレンスホール(東京都)
  • Year and Date: 2011-08-02
• [Presentation] "日本語言語資源の統合的相互運用" (2011)
  • Author(s): 狩野芳伸, 橋田浩一
  • Organizer: 言語処理学会第17回年次大会
  • Place of Presentation: 豊橋技術科学大学
  • Year and Date: 2011-03-10
• [Presentation] 日本語言語資源の統合的相互運用 (2011)
  • Author(s): 狩野芳伸, 橋田浩一
  • Organizer: 言語処理学会第17回年次大会
  • Place of Presentation: 豊橋技術科学大学
  • Year and Date: 2011-03-10
• [Presentation] "自然言語処理プラットフォームの現状と利用" (2010)
  • Author(s): 狩野芳伸
  • Organizer: 英語コーパス学会第36回大会シンポジウム
  • Place of Presentation: 東京大学駒場キャンパス 招待講演
  • Year and Date: 2010-10-09
• [Presentation] 自然言語処理プラットフォームの現状と利用 (2010)
  • Author(s): 狩野芳伸
  • Organizer: 英語コーパス学会第36回大会シンポジウム
  • Place of Presentation: 東京大学駒場キャンパス 招待講演
  • Year and Date: 2010-10-09
• [Presentation] "U-Compare: An integrated language resource evaluation platform including a comprehensive UIMA resource library" (2010)
  • Author(s): Yoshinobu Kano, Ruben Dorado, Luke McCrohon, Sophia Ananiadou, Jun'ichi Tsujii
  • Organizer: Seventh International Conference on Language Resources and Evaluation (LREC 2010)
  • Place of Presentation: Valletta, Malta
  • Year and Date: 2010-05-19
• [Presentation] U-Compare : An integrated language resource evaluation platform including a comprehensive UIMA resource library (2010)
  • Author(s): Kano, Yoshinobu, Ruben Dorado, Luke McCrohon, Sophia Ananiadou, Jun'ichi Tsujii
  • Organizer: Seventh International Conference on Language Resources and Evaluation (LREC 2010)
  • Place of Presentation: Valletta, Malta
  • Year and Date: 2010-05-19
• [Presentation] "AkaneRE Relation Extraction : Protein Interaction and Normalization in the BioCreAtIvE II.5 Challenge" (2009)
  • Author(s): Rune Saetre, Kazuhiro Yoshida, Makoto Miwa, Takuya Matsuzaki, Yoshinobu Kano, Jun'ichi Tsujii
  • Organizer: In the BioCreative II.5 Workshop 2009 special session | Digital Annotations
  • Place of Presentation: Madrid, Spain
  • Year and Date: 2009-10-08
• [Presentation] "Integrated NLP Evaluation System for Pluggable Evaluation Metrics with Extensive Interoperable Toolkit (査読有)" (2009)
  • Author(s): Yoshinobu Kano, Luke McCrohon, Sophia Ananiadou, and Jun'ichi Tsujii
  • Organizer: In the Software engineering, testing, and quality assurance for natural language processing workshop (SETQA-NLP), the 2009 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)
  • Place of Presentation: Boulder, Colorado, USA
  • Year and Date: 2009-06-05
• [Presentation] "Overview of BioNLP'09 Shared Task on Event Extraction" (2009)
  • Author(s): Jin-Dong Kim, Tomoko Ohta, Sampo Pyysalo, Yoshinobu Kano, and Jun'ichi Tsujii
  • Organizer: In the Proceedings of the BioNLP 2009 Workshop Companion Volume for Shared Task
  • Place of Presentation: Boulder, Colorado, USA
  • Year and Date: 2009-06-05
• [Presentation] Integrated NLP Evaluation System for Pluggable Evaluation Metrics with Extensive Interoperable Toolkit (査読有) (2009)
  • Author(s): Kano, Yoshinobu, Luke McCrohon, Sophia Ananiadou, Jun'ichi Tsujii
  • Organizer: In the Software engineering, testing, and quality assurance for natural language processing workshop (SETQA-NLP), NAACL-HLT
  • Place of Presentation: Boulder, Colorado, USA
• [Presentation] Overview of BioNLP'09 Shared Task on Event Extraction (2009)
  • Author(s): Kim, Jin-Dong, Tomoko Ohta, Sampo Pyysalo, Yoshinobu Kano, Jun'ichi Tsujii
  • Organizer: n the Proceedings of the BioNLP 2009 Workshop Companion Volume for Shared Task
  • Place of Presentation: Boulder, Colorado, USA
• [Presentation] AkaneRE Relation Extraction : Protein Interaction and Normalization in the BioCreAtIvE II.5 Challenge (2009)
  • Author(s): Saetre, Rune, Kazuhiro Yoshida, Makoto Miwa, Takuya Matsuzaki, Yoshinobu Kano, Jun'ichi Tsujii
  • Organizer: In the BioCreative II.5 Workshop 2009 special session | Digital Annotations
  • Place of Presentation: Madrid, Spain
• [Presentation] BCCWJと関連ツールの相互運用
  • Author(s): 狩野芳伸, 橋田浩一
  • Organizer: 『現代日本語書き言葉均衡コーパス』完成記念講演会
  • Place of Presentation: JA共済ビルカンファレンスホール（東京都）
  • Invited