The saurus construction using corpus of science and technology and its application to document retrieval

• Project/Area Number: 20500127
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Single-year Grants
• Section: 一般
• Research Field: Intelligent informatics
• Research Institution: University of Yamanashi
• Principal Investigator: SUZUKI Yoshimi University of Yamanashi, 大学院・医学工学総合研究部, 准教授 (20206551)
• Project Period (FY): 2008 – 2010
• Project Status: Completed (Fiscal Year 2010)
• Budget Amount: ¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000); Fiscal Year 2010: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000); Fiscal Year 2009: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000); Fiscal Year 2008: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
• Keywords: 自然言語処理 / 情報検索 / シソーラス / 類義語 / 関連文書抽出 / 特許公報文 / コーパス / 上位 / 下位概念 / 同属語 / 単語間類似度 / 固有名詞 / 上位概念 / 新聞記事

Research Abstract

We studied thesaurus expansion using patent documents and document retrieval using the expanded thesaurus. In particular, using patent documents we investigated the following 4 subtasks : (1) extraction of similar word pairs, (2) classification of the extracted similar word pairs, (3) thesaurus expansion using the extracted similar word pairs, and (4) document retrieval using the expanded thesaurus.

Research Products

• [Journal Article] Polysemous Verb Classification using Subcategorization Acquisition and Graph-based Clustering (2011)
  • Author(s): F.Fukumoto, Y.Suzuki, K.Yamashita
  • Journal Title: Human Language Technologies, Lecture Notes in Computer Science (To Appear)
  • Peer Reviewed
• [Journal Article] Identifying Domain-Specific Senses and its Application to Text Classification (2010)
  • Author(s): F.Fukumoto, Y.Suzuki
  • Journal Title: Proc. of 2nd International Conference on Knowledge Engineering and Ontology Development Pages: 59-64
  • Peer Reviewed
• [Journal Article] Eliminating Redundancy by Spectral Relaxation for Multi-Documents Summarization (2010)
  • Author(s): F.Fukumoto, A.Sakai, Y.Suzuki
  • Journal Title: Proc. of 2010 Workshop on Graph-based Methods for Natural Language Processing Pages: 98-102
  • Peer Reviewed
• [Journal Article] Integrating Technical Terms into Thesaurus using Extracted Related Words (2010)
  • Author(s): Y.Suzuki, F.Fukumoto
  • Journal Title: Proceedings of the International Symposium on Matching and Meaning Pages: 34-38
  • Peer Reviewed
• [Journal Article] Integrating Technical Terms into Thesaurus using Extracted Related Words (2010)
  • Author(s): Yoshimi Suzuki
  • Journal Title: Proceedings of the International Symposium on Matching and Meaning Pages: 34-38
  • Peer Reviewed
• [Journal Article] Identifying Domain-Specific Senses and its Application to Text Classification (2010)
  • Author(s): Fumiyo Fukumoto
  • Journal Title: Proc. of 2nd International Conference on Knowledge Engineering and Ontology Development Pages: 59-64
  • Peer Reviewed
• [Journal Article] Integrating Technical Terms into Thesaurus using Extracted Related Words (2010)
  • Author(s): Yoshimi Suzuki
  • Journal Title: AISB2010 Proceedings of the International Symposium on Matching and Meaning Automated Development, Evolution and Interpretation of Ontologies Pages: 34-38
  • Peer Reviewed
• [Journal Article] Classifying Polysemies using a Graph-based Clustering (2009)
  • Author(s): F.fukumoto, K.Yamashita, Y.Suzuki
  • Journal Title: Proc. of the 4th Language and Technology Conference Pages: 210-214
  • Peer Reviewed
• [Journal Article] Effect of Overt Pronoun Resolution in Topic Tracking (2009)
  • Author(s): F.Fukumoto, Y.Suzuki
  • Journal Title: Proc, of the 4th Language and Technology Conference Pages: 350-354
  • Peer Reviewed
• [Journal Article] Using Graph-based Indexing to Identify Subject-Shift in Topic Tracking (2009)
  • Author(s): F.Fukumoto, Y.Suzuki
  • Journal Title: Human Language Technologies, Lecture Notes in Computer Science Vol. 5603 Pages: 392-404
  • Peer Reviewed
• [Journal Article] Detecting Word Senses of Technical Terms in Patent Documents using Hierarchical Semantic Features (2009)
  • Author(s): Y.Suzuki, F.Fukumoto
  • Journal Title: Proceedings of 4th Language, Technology Conference Pages: 195-199
  • Peer Reviewed
• [Journal Article] Classifying Japanese Polysemous Verbs based on Fuzzy C-means Clustering (2009)
  • Author(s): Y.Suzuki, F.Fukumoto
  • Journal Title: Proceedings of the 2009 Workshop on Graph-based Methods for Natural Language Processing (TextGraphs-4) Pages: 32-40
  • Peer Reviewed
• [Journal Article] Example-assignment to WordNet Thesaurus based on Distributional Similarity of Words (2009)
  • Author(s): F.Fukumoto, N.A.H.B.Zahri, Y.Suzuki
  • Journal Title: Proc. of Workshop on Matching and Meaning Pages: 1-5
  • Peer Reviewed
• [Journal Article] Detecting unknown word senses using concept dictionary (2009)
  • Author(s): Y.Suzuki, F.Fukumoto
  • Journal Title: Proceedings of the Symposium on Matching and Meaning Pages: 49-51
  • Peer Reviewed
• [Journal Article] Detecting Word Senses of Technical Terms in Patent Documents using Hierarchical Semantic Features (2009)
  • Author(s): Yoshimi Suzuki
  • Journal Title: Proceedings of 4^<th> Language & Technology Conference Pages: 195-199
  • Peer Reviewed
• [Journal Article] Classifying Japanese Polysemous Verbs based on Fuzzy C-means Clustering (2009)
  • Author(s): Yoshimi Suzuki
  • Journal Title: Proceedings of the 2009 Workshop on Graph-based Methods for Natural Language Processing Pages: 32-40
  • Peer Reviewed
• [Journal Article] Detecting unknown word senses using concept dietionary (2009)
  • Author(s): Y. Suzuki
  • Journal Title: Proc. of Workshop on Matching and Meaning Pages: 49-51
  • Peer Reviewed
• [Journal Article] The Effect of Combining Similarity Measures for Onomatopieia Clustering (2008)
  • Author(s): F.Fukumoto, Y.Suzuki
  • Journal Title: Proc. of Empirical Method in Asian Natural Language Processing Pages: 37-51
  • Peer Reviewed
• [Journal Article] Retrieving Bilingual Verb-Noun Collocations by Integrating Cross-Language Category Hierarchies (2008)
  • Author(s): F.Fukumoto, Y.Suzuki
  • Journal Title: Proc. of the 22nd International Conference on Computational Linguistics Pages: 233-240
  • Peer Reviewed
• [Journal Article] Integrating Cross-Language Hierarchies and its Application to Retrieving Relevant Documents (2008)
  • Author(s): F.Fukumoto, Y.Suzuki
  • Journal Title: ACM Trans. of Asian Language Information Processing 7(3) Pages: 1-22
  • Peer Reviewed
• [Presentation] Web上のオノマトペの用例を共起単語で絞り込む用例抽出法 (2010)
  • Author(s): 森田一匡
  • Organizer: 言語処理学会 第16回年次大会
  • Place of Presentation: 東京都 東京大学 本郷キャンパス
  • Year and Date: 2010-03-12
• [Presentation] Web上のオノマトペの用例を共起単語で絞り込む用例抽出法 (2010)
  • Author(s): 森田一匡, 鈴木良弥
  • Organizer: 言語処理学会第16回年次大会講演論文集
  • Place of Presentation: 東京大学
  • Year and Date: 2010-03-08