Stance Detection Attending External Knowledge from Wikipedia

• Item type: Trans(1)
• 公開日: 2019-07-17
• タイトル: Stance Detection Attending External Knowledge from Wikipedia
• タイトル / 言語: en
• タイトル: Stance Detection Attending External Knowledge from Wikipedia
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: [研究論文] natural language processing, opinion mining, stance detection, world knowledge
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_6501
• 資源タイプ: journal article
• 著者所属: RIKEN Center for Advanced Intelligence Project／Tohoku University
• 著者所属: Recruit Technologies Co., Ltd.
• 著者所属: Tokyo Institute of Technology
• 著者所属: RIKEN Center for Advanced Intelligence Project／Tohoku University
• 著者所属(英): en
• 著者所属(英): RIKEN Center for Advanced Intelligence Project / Tohoku University
• 著者所属(英): en
• 著者所属(英): Recruit Technologies Co., Ltd.
• 著者所属(英): en
• 著者所属(英): Tokyo Institute of Technology
• 著者所属(英): en
• 著者所属(英): RIKEN Center for Advanced Intelligence Project / Tohoku University
• 著者名: Kazuaki, Hanawa; Akira, Sasaki; Naoaki, Okazaki; Kentaro, Inui
• 著者名(英): Kazuaki, Hanawa; Akira, Sasaki; Naoaki, Okazaki; Kentaro, Inui
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: This paper presents a novel approach to stance detection for unseen topics that takes advantage of external knowledge about the topics. We build a new stance detection dataset consisting of 6,701 tweets on seven topics with associated Wikipedia articles. An analysis of this dataset confirms the necessity of external knowledge for this task. This paper also presents a method of extracting related concepts and events from Wikipedia articles. To incorporate this extracted knowledge into stance detection, we propose a novel neural network model that can attend to such related concepts and events when encoding the given text using bi-directional long short-term memories. Our experimental results demonstrate that the proposed method, using knowledge extracted from Wikipedia, can improve stance detection performance.; ------------------------------; This is a preprint of an article intended for publication Journal of; Information Processing(JIP). This preprint should not be cited. This; article should be cited as: Journal of Information Processing Vol.27(2019) (online); ------------------------------
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: This paper presents a novel approach to stance detection for unseen topics that takes advantage of external knowledge about the topics. We build a new stance detection dataset consisting of 6,701 tweets on seven topics with associated Wikipedia articles. An analysis of this dataset confirms the necessity of external knowledge for this task. This paper also presents a method of extracting related concepts and events from Wikipedia articles. To incorporate this extracted knowledge into stance detection, we propose a novel neural network model that can attend to such related concepts and events when encoding the given text using bi-directional long short-term memories. Our experimental results demonstrate that the proposed method, using knowledge extracted from Wikipedia, can improve stance detection performance.; ------------------------------; This is a preprint of an article intended for publication Journal of; Information Processing(JIP). This preprint should not be cited. This; article should be cited as: Journal of Information Processing Vol.27(2019) (online); ------------------------------
• 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: AA11464847
• 書誌情報: 情報処理学会論文誌データベース（TOD）; 巻 12, 号 3, 発行日 2019-07-17
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 1882-7799
• 出版者 / 言語: ja
• 出版者: 情報処理学会