{"created":"2025-01-19T00:36:01.068142+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00164173","sets":["6504:8291:8753"]},"path":["8753"],"owner":"6748","recid":"164173","title":["Content Reuse Detection in Text Documents"],"pubdate":{"attribute_name":"公開日","attribute_value":"2015-03-17"},"_buckets":{"deposit":"1f79532a-ddeb-470d-9f3d-0fb6c532ff79"},"_deposit":{"id":"164173","pid":{"type":"depid","value":"164173","revision_id":0},"owners":[6748],"status":"published","created_by":6748},"item_title":"Content Reuse Detection in Text Documents","author_link":["323052","323051","323053"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Content Reuse Detection in Text Documents"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"データとウェブ","subitem_subject_scheme":"Other"}]},"item_type_id":"22","publish_date":"2015-03-17","item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"eng"}]},"item_22_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"名大"},{"subitem_text_value":"名大"},{"subitem_text_value":"名大"}]},"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/164173/files/IPSJ-Z77-5N-04.pdf","label":"IPSJ-Z77-5N-04.pdf"},"date":[{"dateType":"Available","dateValue":"2016-06-10"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-Z77-5N-04.pdf","filesize":[{"value":"115.2 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"8"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"4f7bb47d-46a6-47d7-a1ed-22f2ae08285d","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2015 by the Information Processing Society of Japan"}]},"item_22_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"王, 沛"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"肖, 川"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"石川, 佳治"}],"nameIdentifiers":[{}]}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_5794","resourcetype":"conference paper"}]},"item_22_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN00349328","subitem_source_identifier_type":"NCID"}]},"item_22_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"Text document collection typically contains reused information. Events or facts may be restated with modifications by various sources. Identifying text reuse may help to find original sources of facts and track information flow, and thus becomes an important task in text analysis. In this paper, we study the problem of content reuse detection in text documents. Existing methods are usually sensitive to modifications such as paraphrases and miss many meaningful results in this case. We propose a new method that tolerates a considerable amount of differences in reused contents. A prefix-filtering-based algorithm is devised for efficient reuse detection. Experiment evaluation on real datasets demonstrates that our method outperforms alternative solutions in terms of both effectiveness and efficiency.","subitem_description_type":"Other"}]},"item_22_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"670","bibliographic_titles":[{"bibliographic_title":"第77回全国大会講演論文集"}],"bibliographicPageStart":"669","bibliographicIssueDates":{"bibliographicIssueDate":"2015-03-17","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2015"}]},"relation_version_is_last":true,"weko_creator_id":"6748"},"id":164173,"updated":"2025-01-20T11:02:06.359357+00:00","links":{}}