{"updated":"2025-01-21T18:56:03.913638+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00082618","sets":["581:6644:6801"]},"path":["6801"],"owner":"11","recid":"82618","title":["機械翻訳の品質向上のための対訳コーパスからの統計的前編集システムの自動構築"],"pubdate":{"attribute_name":"公開日","attribute_value":"2012-06-15"},"_buckets":{"deposit":"694afe1c-e161-45c0-a59e-d409ea444d98"},"_deposit":{"id":"82618","pid":{"type":"depid","value":"82618","revision_id":0},"owners":[11],"status":"published","created_by":11},"item_title":"機械翻訳の品質向上のための対訳コーパスからの統計的前編集システムの自動構築","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"機械翻訳の品質向上のための対訳コーパスからの統計的前編集システムの自動構築"},{"subitem_title":"Automatic Construction of Statistical Pre-editing System from Parallel Corpus for Improvement of Machine Translation Quality","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"[一般論文] 統計的前編集，書き換え，学習データ選択，機械翻訳","subitem_subject_scheme":"Other"}]},"item_type_id":"2","publish_date":"2012-06-15","item_2_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"龍谷大学理工学部"},{"subitem_text_value":"龍谷大学理工学研究科"},{"subitem_text_value":"龍谷大学理工学部"}]},"item_2_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Faculty of Science and Technology, Ryukoku University","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Science and Technology, Ryukoku University","subitem_text_language":"en"},{"subitem_text_value":"Faculty of Science and Technology, Ryukoku University","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/82618/files/IPSJ-JNL5306021.pdf"},"date":[{"dateType":"Available","dateValue":"2014-06-15"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-JNL5306021.pdf","filesize":[{"value":"1.7 MB"}],"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":"d3233a13-92a2-499a-b6d7-c28d2df447c2","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2012 by the Information Processing Society of Japan"}]},"item_2_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"南條浩輝"},{"creatorName":"山本, 祐司"},{"creatorName":"吉見, 毅彦"}],"nameIdentifiers":[{}]}]},"item_2_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Hiroaki, Nanjo","creatorNameLang":"en"},{"creatorName":"Yuji, Yamamoto","creatorNameLang":"en"},{"creatorName":"Takehiko, Yoshimi","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":"機械翻訳（MT）の品質向上のための翻訳前の書き換え（前編集）について述べる．これまでの前編集は主にルールに基づくものであるため，MTシステムに依存し，かつシステム構築に労力を要した．これに対し，本論文では，MTシステムに依存しない統計的前編集システムの自動構築手法を提案する．具体的には，対象とするMTシステムに適した前編集システムを，当該MTシステムを含む複数のMTシステムおよび対訳コーパスから自動構築する手法を提案する．本手法の最も重要な特徴は，前編集によって翻訳品質の向上が得られる学習データを自動生成できる点にある．ロイター日英記事の対応付けデータを用いて4種類の日英MTシステム用前編集システムを構築したところ，3種類のMTシステムについて，多くの文に対して翻訳品質を向上させる前編集システムが構築できた．提案手法である前編集システムの学習データの自動生成は，3種類のMTシステムの前編集システム構築に効果的であったこと，および他の1種類のMTシステムの前編集システム構築に悪影響がなかったことを示し，提案手法の有効性を示した．","subitem_description_type":"Other"}]},"item_2_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Rewriting before machine translation (MT), namely pre-editing, is addressed. Most of conventional pre-editings are MT dependent rule-based systems, and construction of such systems costs too much. In this paper, we propose an automatic construction method of MT independent statistical pre-editing systems. Specifically, for a specific MT system, statistical pre-editing system is trained with appropriate training data which are automatically generated with parallel corpus and some MT systems including the target MT system. Using Reuters Japanese-English parallel corpus, effective pre-editing systems were automatically constructed for several Japanese to English MT systems. We showed the effectiveness of the proposed method.","subitem_description_type":"Other"}]},"item_2_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"1653","bibliographic_titles":[{"bibliographic_title":"情報処理学会論文誌"}],"bibliographicPageStart":"1644","bibliographicIssueDates":{"bibliographicIssueDate":"2012-06-15","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"6","bibliographicVolumeNumber":"53"}]},"relation_version_is_last":true,"weko_creator_id":"11"},"created":"2025-01-18T23:36:27.374498+00:00","id":82618,"links":{}}