Link Analysis Approaches to Natural Language Processing and Text Mining

• Project/Area Number: 21500141
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Single-year Grants
• Section: 一般
• Research Field: Intelligent informatics
• Research Institution: Nara Institute of Science and Technology
• Principal Investigator: SHIMBO Masashi 奈良先端科学技術大学院大学, 情報科学研究科, 准教授 (90311589)
• Project Period (FY): 2009 – 2011
• Project Status: Completed (Fiscal Year 2011)
• Budget Amount: ¥4,550,000 (Direct Cost: ¥3,500,000、Indirect Cost: ¥1,050,000); Fiscal Year 2011: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000); Fiscal Year 2010: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000); Fiscal Year 2009: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
• Keywords: 自然言語処理 / データマイニング / テキストマ / リンク解析 / テキストマイニング / ハブ

Research Abstract

We investigated how to effectively apply link analysis techniques to the tasks of natural language processing. Specifically, we developed a method for analyzing conjunctive structures in natural language sentences. The method borrows an idea from the similarity computation method in link analysis, which counts all paths between the nodes of interest. Our proposed method applied the idea to finding the most similar phrases in a sentence, which are likely to form coordination. We also proposed a graph construction method that reduces the influence of "hubs", which are the nodes located close by to many other nodes in a graph.

Research Products

• [Journal Article] Semi-supervised classification and betweenness computation on large, sparse, directed graphs. (2011)
  • Author(s): Amin Mantrach, Nicholas van Zeebroeck, Pascal Francq, Masashi Shimbo, Shimbo, Hughes Bersini, and Marco Saerens
  • Journal Title: Pattern Recognition Volume: Vol.44 Pages: 1212-1224
  • Peer Reviewed
• [Journal Article] A sum-over-paths extension of edit distances accounting for all sequence alignments. (2011)
  • Author(s): Silvia Garcia-Diez, Francois Fouss, Masashi Shimbo, and Marco Saerens
  • Journal Title: Pattern Recognition Volume: Vol.44 Pages: 1172-1182
  • Peer Reviewed
• [Journal Article] Semi-supervised classification and betweenness computation on large, sparse, directed graphs (2011)
  • Author(s): A.Mantrach/N.van Zeebroeck/P.Francq/M.Shimbo/H.Bersini/M.Saerens
  • Journal Title: Pattern Recognition Volume: 44 Pages: 1212-1224
  • Peer Reviewed
• [Journal Article] A sum-over-paths extension of edit distances accounting for all sequence alignments (2011)
  • Author(s): S.Garcia-Diez/F.Fouss/M.Shimbo/M.Saerens
  • Journal Title: Pattern Recognition Volume: 44 Pages: 1172-1182
  • Peer Reviewed
• [Journal Article] The sum-over-paths covariance kernel : a novel covariance measure between nodes of a directed graph (2010)
  • Author(s): Amin Mantrach, Luh Yen, Jerome Callut, Kevin Francoisse, Masashi Shimbo, and Marco Saerens
  • Journal Title: IEEE Transactions on Pattern Analysis and Machine Intelligence Volume: Vol.32 Pages: 1112-1126
  • Peer Reviewed
• [Journal Article] 文法制約と系列アラインメントによる並列構造の解析 (2010)
  • Author(s): 原一夫, 新保仁, 松本裕治
  • Journal Title: 人工知能学会論文誌 Volume: Vol.25 Pages: 560-569
  • NAID: 130000308089
  • Peer Reviewed
• [Journal Article] バイパス付きアラインメントグラフを用いた日本語並列句検出と範囲同定 (2010)
  • Author(s): 大熊秀治, 原一夫, 新保仁, 松本裕治
  • Journal Title: 人工知能学会論文誌 Volume: Vol.25 Pages: 206-214
  • NAID: 130000151251
  • Peer Reviewed
• [Journal Article] Espresso型ブートストラッピング法における意味ドリフトのグラフ理論的分析 (2010)
  • Author(s): 小町守, 工藤拓, 新保仁, 松本裕治
  • Journal Title: 人工知能学会論文誌 Volume: Vol.25 Pages: 233-242
  • Peer Reviewed
• [Journal Article] The sum-over-paths covariance kernel : a novel covariance measure between nodes of a directed graph (2010)
  • Author(s): A.Mantrach, L.Yen, J.Callut, K.Francoisse, M.Shimbo, M.Saerens
  • Journal Title: IEEE Transactions on Pattern Analysis and Machine Intelligence Volume: 32 Pages: 1112-1126
  • Peer Reviewed
• [Journal Article] バイパス付きアラインメントグラフを用いた日本語並列句検出と範囲同定 (2010)
  • Author(s): 大熊秀治, 原一夫, 新保仁, 松本裕治
  • Journal Title: 人工知能学会論文誌 25 Pages: 206-214
  • NAID: 130000151251
  • Peer Reviewed
• [Journal Article] Espresso型ブートストラッピング法における意味ドリフトのグラフ理論的分析 (2010)
  • Author(s): 小町守, 工藤拓, 新保仁, 松本裕治
  • Journal Title: 人工知能学会論文誌 25 Pages: 233-242
  • Peer Reviewed
• [Presentation] Using the mutual k-nearest neighbor graphs for semi-supervised classification of natural language data (2011)
  • Author(s): Kohei Ozaki, Masashi Shimbo, Mamoru Komachi, and Yuji Matsumoto
  • Organizer: Proceedings of the 15th Conference on Natural Language Learning(CoNLL2011)
  • Place of Presentation: Portland, OR, USA
  • Year and Date: 2011-06-23
• [Presentation] Using the mutual k-nearest neighbor graphs for semi-supervised classification of natural language data (2011)
  • Author(s): K.Ozaki/M.Shimbo/M.Komachi/Y.Matsumoto
  • Organizer: 15th CoNLL
  • Place of Presentation: Portland, OR, USA
  • Year and Date: 2011-06-23
• [Presentation] HITS-based seed selection and stop-list construction for bootstrapping (2011)
  • Author(s): Tetsuo Kiso, Masashi Shimbo, Mamoru Komachi, and Yuji Matsumoto
  • Organizer: In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics(ACL2011): Short Papers
  • Place of Presentation: P ortland, OR, USA
  • Year and Date: 2011-06-21
• [Presentation] HITS-based seed selection and stop-list construction for bootstrapping (2011)
  • Author(s): T.Kiso/M.Shimbo/M.Komachi/Y.Matsumoto
  • Organizer: 49th ACL : Short Papers
  • Place of Presentation: Portland, OR, USA
  • Year and Date: 2011-06-21
• [Presentation] Normalized sum-over-paths edit distances (2010)
  • Author(s): S ilvia Garcia Diez, Francois Fouss, Masashi Shimbo, Marco Saerens
  • Organizer: Proceedings of the 2010 International Conference on Pattern Recognition(ICPR2010)
  • Place of Presentation: イスタンブール
  • Year and Date: 2010-08-24
• [Presentation] Normalized sum-over-paths edit distances (2010)
  • Author(s): Silvia Garcia Diez, Francois Fouss, Masashi Shimbo, Marco Saerens
  • Organizer: International Conference on Pattern Recognition
  • Place of Presentation: Istanbul, Turkey
  • Year and Date: 2010-08-24
• [Presentation] A Graph-based Approach for Biomedical Thesaurus Expansion (2009)
  • Author(s): Ikumi Suzuki, Kazuo Hara, Masashi Shimbo, and Yuji Matsumoto
  • Organizer: Proceedings of the Third ACM International Workshop on Data and Text Mining in Bioinformatics(DTMBIO)
  • Place of Presentation: 香港
  • Year and Date: 2009-11-06
• [Presentation] A Graph-based Approach for Biomedical Thesaurus Expansion (2009)
  • Author(s): Ikumi Suzuki, Kazuo Hara, Masashi Shimbo, Yuji Matsumoto
  • Organizer: Third ACM International Workshop on Data and Text Mining in Bioinformatics (DTMBIO)
  • Place of Presentation: 香港
  • Year and Date: 2009-11-06
• [Presentation] Coordinate Structure Analysis with Global Structural Constraints and Alignment-Based Local Features (2009)
  • Author(s): Kazuo Hara, Masashi Shimbo, Hideharu Okuma, and Yuji Matsumoto
  • Organizer: 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(ACL-IJCNLP2009)
  • Place of Presentation: シンガポール
  • Year and Date: 2009-08-05
• [Presentation] Coordinate Structure Analysis with Global Structural Constraints and A lignment-Based Local Features (2009)
  • Author(s): Kazuo Hara, Masashi Shimbo, Hideharu Okuma, Yuji Matsumoto
  • Organizer: Joint Conference of the 47th Annual Meeting of the Association for Computational Linguistics, and the 4th International Joint Conference on Natural Language Processing (ACL-IJCNLP 2009)
  • Place of Presentation: シンガポール
  • Year and Date: 2009-08-05
• [Presentation] Bypassed Alignment Graph for Learning Coordination in Japanese Sentences (2009)
  • Author(s): Hideharu Okuma, Kazuo Hara, Masashi Shimbo, and Yuji Matsumoto
  • Organizer: 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(ACL-IJCNLP2009): Short Papers
  • Place of Presentation: シンガポール
  • Year and Date: 2009-08-04
• [Presentation] Bypassed Alignment Graph for Learning Coordination in Japanese Sentences (2009)
  • Author(s): Hideharu Okuma, Kazuo Hara, Masashi Shimbo, Yuji Matsumoto
  • Organizer: Joint Conference of the 47th Annual Meeting of the Association for Computational Linguistics, and the 4th International Joint Conference on Natural Language Processing (ACL-IJCNLP 2009)
  • Place of Presentation: シンガポール
  • Year and Date: 2009-08-04