{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00009274","sets":["581:582:584"]},"path":["584"],"owner":"1","recid":"9274","title":["節の始境界検出に基づく独話文の係り受け解析"],"pubdate":{"attribute_name":"公開日","attribute_value":"2009-02-15"},"_buckets":{"deposit":"e027ab2a-dd15-49db-a0d1-9a948be94046"},"_deposit":{"id":"9274","pid":{"type":"depid","value":"9274","revision_id":0},"owners":[1],"status":"published","created_by":1},"item_title":"節の始境界検出に基づく独話文の係り受け解析","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"節の始境界検出に基づく独話文の係り受け解析"},{"subitem_title":"Dependency Parsing of Spoken Monologue Based on Clause-start Identification","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"特集:音声ドキュメント処理","subitem_subject_scheme":"Other"}]},"item_type_id":"2","publish_date":"2009-02-15","item_2_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"名古屋大学大学院国際開発研究科"},{"subitem_text_value":"名古屋大学情報連携基盤センター,情報通信研究機構音声コミュニケーショングループ"},{"subitem_text_value":"情報通信研究機構音声コミュニケーショングループ,ATR音声言語コミュニケーション研究所"},{"subitem_text_value":"豊橋技術科学大学"}]},"item_2_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Graduate School of International Development, Nagoya University","subitem_text_language":"en"},{"subitem_text_value":"Information Technology Center, Nagoya University,NICT Spoken Language Communication Group","subitem_text_language":"en"},{"subitem_text_value":"NICT Spoken Language Communication Group,ATR Spoken Language Communication Research Laboratories","subitem_text_language":"en"},{"subitem_text_value":"Toyohashi University of Technology","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"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/9274/files/IPSJ-JNL5002012.pdf"},"date":[{"dateType":"Available","dateValue":"2011-02-15"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-JNL5002012.pdf","filesize":[{"value":"295.4 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":"8"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"b02e051e-1ef8-4ea3-8311-380ae1753447","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2009 by the Information Processing Society of Japan"}]},"item_2_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"大野誠寛"},{"creatorName":"松原, 茂樹"},{"creatorName":"柏岡, 秀紀"},{"creatorName":"稲垣, 康善"}],"nameIdentifiers":[{}]}]},"item_2_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Tomohiro, Ohno","creatorNameLang":"en"},{"creatorName":"Shigeki, Matsubara","creatorNameLang":"en"},{"creatorName":"Hideki, Kashioka","creatorNameLang":"en"},{"creatorName":"Yasuyoshi, Inagaki","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_2_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN00116647","subitem_source_identifier_type":"NCID"}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_6501","resourcetype":"journal article"}]},"item_2_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"1882-7764","subitem_source_identifier_type":"ISSN"}]},"item_2_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"1文が長いという特徴を持つ独話文の高性能な係り受け解析を実現するため,節に分割し,節レベルと文レベルの2段階で係り受け解析を実行する枠組みが提案されており,その有効性が確認されている.しかし,上述の枠組みにおいては,節そのものに文を分割することはできないため,節の終境界で挟まれた単位(節境界単位)を解析の処理単位として用いており,そこでは解析単位の内部で係り受けが閉じない場合があることが問題となっていた.本論文では,節レベルと文レベルの2段階で解析を実行する枠組みに基づいて,節境界単位を拡張した完全に係り受けが閉じた単位を解析の処理単位とする係り受け解析手法を提案する.本手法では,ポーズや節境界タイプを考慮して,機械学習により節境界単位で閉じない係り受けの係り文節を検出し,この直後で節境界単位を再分割することにより,係り受けが閉じた単位を同定する.この単位を解析の処理単位として利用することにより,解析精度が改善されることを確認した.","subitem_description_type":"Other"}]},"item_2_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"A dependency parsing method based on sentence segmentation into clauses has been proposed and confirmed to be effective. In this method, dependency parsing is executed in two stages: at the clause level and the sentence level. However, since a sentence can not be segmented into complete clauses, in the past research, a unit sandwiched between two clause-end boundaries (<b>clause boundary unit</b>) is adapted as an approximate unit of the complete clause. There has been a problem that the dependency structure of the clause boundary unit is not necessarily closed. This paper proposes a method for dependency parsing based on sentece segmentation into units which corresponds to clauses and whose dependency structure is completely closed (<b>clause fragment</b>). Our method identifies such the unit by redividing a clause boundary unit at modifier bunsetsus of dependency relations over clause-end boundaries. As the results of the experiment, we confirmed the improvement of the dependency parsing accuracy by utilizing the clause fragment unit as a parsing unit.","subitem_description_type":"Other"}]},"item_2_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"562","bibliographic_titles":[{"bibliographic_title":"情報処理学会論文誌"}],"bibliographicPageStart":"553","bibliographicIssueDates":{"bibliographicIssueDate":"2009-02-15","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"2","bibliographicVolumeNumber":"50"}]},"relation_version_is_last":true,"item_2_alternative_title_2":{"attribute_name":"その他タイトル","attribute_value_mlt":[{"subitem_alternative_title":"情報抽出、構造化"}]},"weko_creator_id":"1"},"id":9274,"updated":"2025-01-23T03:28:13.550742+00:00","links":{},"created":"2025-01-18T22:44:32.201491+00:00"}