{"updated":"2025-01-19T19:32:01.486879+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00206110","sets":["1164:4179:10245:10269"]},"path":["10269"],"owner":"44499","recid":"206110","title":["Graph Attention NetworkによるArgumentationのコンポーネント分類"],"pubdate":{"attribute_name":"公開日","attribute_value":"2020-06-26"},"_buckets":{"deposit":"ee00230c-156c-46b6-8b18-5540871ea9aa"},"_deposit":{"id":"206110","pid":{"type":"depid","value":"206110","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"Graph Attention NetworkによるArgumentationのコンポーネント分類","author_link":["511759","511758"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Graph Attention NetworkによるArgumentationのコンポーネント分類"},{"subitem_title":"Argument Component Classification with Graph Attention Network","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2020-06-26","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"名古屋工業大学"},{"subitem_text_value":"名古屋工業大学"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Nagoya Institute of Technology","subitem_text_language":"en"},{"subitem_text_value":"Nagoya Institute of Technology","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_publisher":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"情報処理学会","subitem_publisher_language":"ja"}]},"publish_status":"0","weko_shared_id":-1,"item_file_price":{"attribute_name":"Billing file","attribute_type":"file","attribute_value_mlt":[{"url":{"url":"https://ipsj.ixsq.nii.ac.jp/record/206110/files/IPSJ-NL20244002.pdf","label":"IPSJ-NL20244002.pdf"},"date":[{"dateType":"Available","dateValue":"2022-06-26"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-NL20244002.pdf","filesize":[{"value":"345.9 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"23"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"ddaa3459-6cb2-4d08-9896-7d4f6c6572b7","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2020 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"鈴木, 祥太"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"伊藤, 孝行"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10115061","subitem_source_identifier_type":"NCID"}]},"item_4_textarea_12":{"attribute_name":"Notice","attribute_value_mlt":[{"subitem_textarea_value":"SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc."}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_18gh","resourcetype":"technical report"}]},"item_4_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"2188-8779","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"議論マイニングは Argumentation を解析し，その構造を特定することを目的とする．議論マイニングにおいて，コンポーネント分類は重要な課題である．コンポーネント分類を行うため，既存の手法は，複雑な議論構造をベクトルのような簡単な表現の特徴量に変換する．しかしながら，これらの特徴量に基づく手法では，複雑な構造を扱う上で貴重な情報が失われると考えられる．この問題を解決するため，本稿では，議論構造を直接的に学習することで，コンポーネント分類を行う手法を提案する．議論構造を直接的に学習するために，提案手法は Graph Attention Network を用いる．提案手法を評価するため，評論のコーパスを用いて実験を行った．実験の結果，提案手法は既存の特徴量に基づく手法よりも正確にコンポーネント分類を行うことが示された．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Argument mining aims to analyze argumentation and identify its argumentative structure. In the field of argument mining, argument component classification is an important task. To address this task, several studies have transformed complex argumentative structures into features of simpler representations such as vectors. However, these feature-based approaches are usually believed to lose valuable information for dealing with these complex structures. To tackle this problem, we propose an approach that performs argument component classification with directly learning argumentative structures. Towards this end, the proposed approach employs a graph attention network. To evaluate the proposed approach, we conducted a set of experiments on a corpus of persuasive essays. The experimental results show that the proposed approach performs argument component classification more accurately than the existing feature-based approaches.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"8","bibliographic_titles":[{"bibliographic_title":"研究報告自然言語処理（NL）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2020-06-26","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"2","bibliographicVolumeNumber":"2020-NL-244"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"created":"2025-01-19T01:08:12.389368+00:00","id":206110,"links":{}}