{"updated":"2025-01-19T18:40:10.211434+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00208954","sets":["1164:1165:10301:10460"]},"path":["10460"],"owner":"44499","recid":"208954","title":["Topic- and Context-Focused Extractive Summarization of Wikipedia sentences by Fine-tuning BERT and Similarity Calculation"],"pubdate":{"attribute_name":"公開日","attribute_value":"2020-12-14"},"_buckets":{"deposit":"2cee2594-e4da-4bab-92c8-dabbf07c5486"},"_deposit":{"id":"208954","pid":{"type":"depid","value":"208954","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"Topic- and Context-Focused Extractive Summarization of Wikipedia sentences by Fine-tuning BERT and Similarity Calculation","author_link":["525485","525486","525483","525484"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Topic- and Context-Focused Extractive Summarization of Wikipedia sentences by Fine-tuning BERT and Similarity Calculation"},{"subitem_title":"Topic- and Context-Focused Extractive Summarization of Wikipedia sentences by Fine-tuning BERT and Similarity Calculation","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"テキスト処理","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2020-12-14","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Information, Production and Systems, Waseda University"},{"subitem_text_value":"Graduate School of Information, Production and Systems, Waseda University"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Information, Production and Systems, Waseda University","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Information, Production and Systems, Waseda University","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"eng"}]},"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/208954/files/IPSJ-DBS20172007.pdf","label":"IPSJ-DBS20172007.pdf"},"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-DBS20172007.pdf","filesize":[{"value":"1.2 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"13"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_login","version_id":"40e620aa-9b66-4bd2-b647-aabe03ab4f90","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2020 by the Institute of Electronics, Information and Communication Engineers This SIG report is only available to those in membership of the SIG."}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Yiqi, Shao"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Mizuho, Iwaihara"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Yiqi, Shao","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Mizuho, Iwaihara","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10112482","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":"2188-871X","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"Wikipedia has been one of the most famous online encyclopedias. Articles' contents in Wikipedia are constantly changing, where new content should be added into an article when a related new event happens. However, news articles about the event are usually too long to be inserted into the article directly, so summarization is necessary. When generating a summary, the title and subtitles that represent the topic of the article, and the context up to the inserting location should be considered. In this paper, we focus on topic- and context-focused extractive summarization which extracts valuable sentences from a news article according to a given topic and context, to form a summary to be inserted. As one of the most popular pretrained language models, BERT has been widely used in various natural language processing tasks, and BERT has been proved to greatly improve the performance of single-document extractive summarization. In this paper, we propose a two-step BERT-based model that can encode the topic and context into their representations for guiding generation of a summary. We conduct evaluations of our model on the benchmark dataset WikiCite and achieved the current state-of-the-art performance.\n","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Wikipedia has been one of the most famous online encyclopedias. Articles' contents in Wikipedia are constantly changing, where new content should be added into an article when a related new event happens. However, news articles about the event are usually too long to be inserted into the article directly, so summarization is necessary. When generating a summary, the title and subtitles that represent the topic of the article, and the context up to the inserting location should be considered. In this paper, we focus on topic- and context-focused extractive summarization which extracts valuable sentences from a news article according to a given topic and context, to form a summary to be inserted. As one of the most popular pretrained language models, BERT has been widely used in various natural language processing tasks, and BERT has been proved to greatly improve the performance of single-document extractive summarization. In this paper, we propose a two-step BERT-based model that can encode the topic and context into their representations for guiding generation of a summary. We conduct evaluations of our model on the benchmark dataset WikiCite and achieved the current state-of-the-art performance.\n","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告データベースシステム（DBS）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2020-12-14","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"7","bibliographicVolumeNumber":"2020-DBS-172"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"created":"2025-01-19T01:10:17.905915+00:00","id":208954,"links":{}}