{"created":"2023-05-15T14:24:45.982094+00:00","id":3283,"links":{},"metadata":{"_buckets":{"deposit":"6d92dca8-a0ae-4742-b200-1eccc1b1932c"},"_deposit":{"created_by":3,"id":"3283","owners":[3],"pid":{"revision_id":0,"type":"depid","value":"3283"},"status":"published"},"_oai":{"id":"oai:repository.ninjal.ac.jp:00003283","sets":["320:324"]},"author_link":["10848","10846","10845","10847"],"item_10001_biblio_info_7":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicIssueDates":{"bibliographicIssueDate":"2020-11","bibliographicIssueDateType":"Issued"},"bibliographicPageEnd":"1357","bibliographicPageStart":"1352","bibliographic_titles":[{},{"bibliographic_title":"Findings of the Association for Computational Linguistics: EMNLP 2020","bibliographic_titleLang":"en"}]}]},"item_10001_description_19":{"attribute_name":"フォーマット","attribute_value_mlt":[{"subitem_description":"application/pdf","subitem_description_type":"Other"}]},"item_10001_description_25":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_description":"Kyoto University","subitem_description_type":"Other"},{"subitem_description":"National Institute for Japanese Language and Linguistics","subitem_description_type":"Other"},{"subitem_description":"Ochanomizu University","subitem_description_type":"Other"},{"subitem_description":"Kyoto University","subitem_description_type":"Other"}]},"item_10001_description_26":{"attribute_name":"抄録(英)","attribute_value_mlt":[{"subitem_description":"Temporal relation classification is a pair-wise task for identifying the relation of a temporal link (TLINK) between two mentions, i.e. event, time and document creation time (DCT). It leads to two crucial limits: 1) Two TLINKs involving a common mention do not share information. 2) Existing models with independent classifiers for each TLINK category (E2E, E2T and E2D) hinder from using the whole data. This paper presents an event centric model that allows to manage dynamic event representations across multiple TLINKs. Our model deals with three TLINK categories with multi-task learning to leverage the full size of data. The experimental results show that our proposal outperforms state-of-the-art models and two transfer learning baselines on both the English and Japanese data.","subitem_description_type":"Other"}]},"item_10001_publisher_8":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"Association for Computational Linguistics"}]},"item_10001_relation_14":{"attribute_name":"DOI","attribute_value_mlt":[{"subitem_relation_type":"isIdenticalTo","subitem_relation_type_id":{"subitem_relation_type_id_text":"10.18653/v1/2020.findings-emnlp.121","subitem_relation_type_select":"DOI"}}]},"item_10001_version_type_20":{"attribute_name":"著者版フラグ","attribute_value_mlt":[{"subitem_version_resource":"http://purl.org/coar/version/c_970fb48d4fbd8a85","subitem_version_type":"VoR"}]},"item_creator":{"attribute_name":"著者","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Cheng, Fei","creatorNameLang":"en"}],"nameIdentifiers":[{"nameIdentifier":"10845","nameIdentifierScheme":"WEKO"}]},{"creatorNames":[{"creatorName":"Asahara, Masayuki","creatorNameLang":"en"}],"nameIdentifiers":[{"nameIdentifier":"10846","nameIdentifierScheme":"WEKO"}]},{"creatorNames":[{"creatorName":"Kobayashi, Ichiro","creatorNameLang":"en"}],"nameIdentifiers":[{"nameIdentifier":"10847","nameIdentifierScheme":"WEKO"}]},{"creatorNames":[{"creatorName":"Kurohashi, Sadao","creatorNameLang":"en"}],"nameIdentifiers":[{"nameIdentifier":"10848","nameIdentifierScheme":"WEKO"}]}]},"item_files":{"attribute_name":"ファイル情報","attribute_type":"file","attribute_value_mlt":[{"accessrole":"open_date","date":[{"dateType":"Available","dateValue":"2021-03-25"}],"displaytype":"detail","filename":"2020.findings-emnlp.121.pdf","filesize":[{"value":"500.6 kB"}],"format":"application/pdf","licensetype":"license_note","mimetype":"application/pdf","url":{"label":"2020.findings-emnlp.121.pdf","url":"https://repository.ninjal.ac.jp/record/3283/files/2020.findings-emnlp.121.pdf"},"version_id":"669cc622-9056-428b-a70a-54a851924be0"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"eng"}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourcetype":"journal article","resourceuri":"http://purl.org/coar/resource_type/c_6501"}]},"item_title":"Dynamically Updating Event Representations for Temporal Relation Classification with Multi-category Learning","item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Dynamically Updating Event Representations for Temporal Relation Classification with Multi-category Learning","subitem_title_language":"en"}]},"item_type_id":"10001","owner":"3","path":["324"],"pubdate":{"attribute_name":"公開日","attribute_value":"2021-03-26"},"publish_date":"2021-03-26","publish_status":"0","recid":"3283","relation_version_is_last":true,"title":["Dynamically Updating Event Representations for Temporal Relation Classification with Multi-category Learning"],"weko_creator_id":"3","weko_shared_id":-1},"updated":"2023-05-15T15:06:06.892761+00:00"}