E-055 Annotating Semantic Structure of Web Text based on CDL.nl

• Item type: FIT(1)
• 公開日: 2008-08-20
• タイトル / 言語: en
• タイトル: E-055 Annotating Semantic Structure of Web Text based on CDL.nl
• 言語: eng
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_5794
• 資源タイプ: conference paper
• 著者所属: 東大
• 著者所属: 東大
• 著者所属: 東大
• 著者所属: 東京工科大
• 著者所属(英): en
• 著者所属(英): The University of Tokyo
• 著者所属(英): en
• 著者所属(英): The University of Tokyo
• 著者所属(英): en
• 著者所属(英): The University of Tokyo
• 著者所属(英): en
• 著者所属(英): Tokyo University of Technology
• 著者名: イェン, ユイラン; 松尾, 豊; 石塚, 満; 横井, 俊夫
• 著者名(英): Yan, Yulan; Matsuo, Yutaka; Ishizuka, Mitsuru; Yokoi, Toshio
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: Confronting the challenges of annotating naturally occurring text into a semantically structured form to facilitate automatic information extraction, based on the Concept Description Language for Natural Language (CDL.nl) which is intended to describe the concept structure of text using a set of pre-defined semantic relations, we develop a parser to add a new layer of semantic annotation of natural language sentences as an extension of SRL (Semantic Role Labeling). The parsing task is a relation extraction process with two steps: relation detection and relation classification. We advance a hybrid approach using different methods for two steps: first, based on dependency analysis, a rule-based method is presented to detect all entity pairs between each pair for which there exists a relationship; secondly, we use a feature-based method to assign a CDL.nl relation to each detected entity pair using Support Vector Machine. We report the preliminary experimental results carried out on our manual dataset annotated with CDL.nl relations.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AA1242354X
• 書誌情報: 情報科学技術フォーラム講演論文集; 巻 7, 号 2, p. 265-266, 発行日 2008-08-20
• 出版者 / 言語: ja
• 出版者: 情報処理学会