{"links":{},"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00048336","sets":["1164:4179:4215:4221"]},"path":["4221"],"owner":"1","recid":"48336","title":["日英対訳パターンの自動抽出に向けて"],"pubdate":{"attribute_name":"公開日","attribute_value":"2003-01-20"},"_buckets":{"deposit":"dc3831e9-3273-4141-b6fc-2e952b216c26"},"_deposit":{"id":"48336","pid":{"type":"depid","value":"48336","revision_id":0},"owners":[1],"status":"published","created_by":1},"item_title":"日英対訳パターンの自動抽出に向けて","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"日英対訳パターンの自動抽出に向けて"},{"subitem_title":"Towards automatic extraction of Japanese/English expression pattern - pairs","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2003-01-20","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"鳥取大学工学部"},{"subitem_text_value":"鳥取大学工学部"},{"subitem_text_value":"鳥取大学工学部"},{"subitem_text_value":"鳥取大学工学部"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Faculty of Engineering, Tottori University","subitem_text_language":"en"},{"subitem_text_value":"Faculty of Engineering, Tottori University","subitem_text_language":"en"},{"subitem_text_value":"Faculty of Engineering, Tottori University","subitem_text_language":"en"},{"subitem_text_value":"Faculty of Engineering, Tottori University","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"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/48336/files/IPSJ-NL02153015.pdf"},"date":[{"dateType":"Available","dateValue":"2005-01-20"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-NL02153015.pdf","filesize":[{"value":"170.2 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":"23"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"b9a14c88-ddfb-4e5d-aeb1-b6d7391c0242","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2003 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"道祖尾太祐"},{"creatorName":"村上, 仁一"},{"creatorName":"徳久, 雅人"},{"creatorName":"池原, 悟"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Daisuke, Sainoo","creatorNameLang":"en"},{"creatorName":"Jin-Ichi, Murakami","creatorNameLang":"en"},{"creatorName":"Masato, Tokuhisa","creatorNameLang":"en"},{"creatorName":"Satoru, Ikehara","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10115061","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_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"意味のまとまりを持つ表現を用いた機械翻訳方式が注目されている．その実現には原言語と目的言語の表現を対としたパターンを大量に作成する必要がある．ここで，表現対の意味的対応は人手で判断するため，その対応関係のありうる表現対に絞り込むべきである．そこで，本研究では，パターン候補の自動作成手法を提案する．具体的には，日英対訳コーパスにN-gram 統計処理を用いて日本語文および英語文から別々に部分表現を取り出し，対訳の関係を利用して表現の対を作りパターンの候補とする．初期の実験として，単文対からなる日英対訳コーパスから候補を作成したところ，約6割の候補は人手による容易な判別でパターン化できることを確認した．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Large semantical expression pattern-pairs are required for a pattern based machine translation.  As the semantical relation between a source language expression and a target one must be inspected by hand, it is necessary to assist in extraction of possible pattern-pairs. This paper proposes an automatic extraction method for candidates of the pairs from Japanese/English parallel corpus as follows: First Japanese and English expression are independently picked up from the corpus.  Next these expressions are connected each other based on the corpus number.  In our preliminary experiment","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"118","bibliographic_titles":[{"bibliographic_title":"情報処理学会研究報告自然言語処理（NL）"}],"bibliographicPageStart":"113","bibliographicIssueDates":{"bibliographicIssueDate":"2003-01-20","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"4(2002-NL-153)","bibliographicVolumeNumber":"2003"}]},"relation_version_is_last":true,"weko_creator_id":"1"},"created":"2025-01-18T23:13:36.454036+00:00","updated":"2025-01-22T08:33:26.832882+00:00","id":48336}