[ { "key": "C8ZBAQWU", "version": 1, "library": { "type": "group", "id": 5316, "name": "Japanese-English Web Parallel Corpus", "links": { "alternate": { "href": "https://www.zotero.org/groups/japanese-english_web_parallel_corpus", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/5316/items/C8ZBAQWU", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/japanese-english_web_parallel_corpus/items/C8ZBAQWU", "type": "text/html" } }, "meta": { "createdByUser": { "id": 45026, "username": "ceekz", "name": "Mitsuo Yoshida", "links": { "alternate": { "href": "https://www.zotero.org/ceekz", "type": "text/html" } } }, "creatorSummary": "Do et al.", "parsedDate": "2009-03", "numChildren": 0 }, "data": { "key": "C8ZBAQWU", "version": 1, "itemType": "conferencePaper", "title": "Mining a Comparable Text Corpus for a Vietnamese-French Statistical Machine Translation System", "creators": [ { "creatorType": "author", "firstName": "Thi Ngoc Diep", "lastName": "Do" }, { "creatorType": "author", "firstName": "Viet Bac", "lastName": "Le" }, { "creatorType": "author", "firstName": "Brigitte", "lastName": "Bigi" }, { "creatorType": "author", "firstName": "Laurent", "lastName": "Besacier" }, { "creatorType": "author", "firstName": "Eric", "lastName": "Castelli" } ], "abstractNote": "", "proceedingsTitle": "Proceedings of the Fourth Workshop on Statistical Machine Translation", "conferenceName": "", "publisher": "Association for Computational Linguistics", "place": "Athens, Greece", "date": "March 2009", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "165–172", "series": "", "seriesNumber": "", "DOI": "", "ISBN": "", "citationKey": "", "url": "http://www.statmt.org/wmt09/pdf/WMT-0930.pdf", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2009-10-02T10:05:56Z", "dateModified": "2009-10-09T13:33:46Z" } }, { "key": "B69PTRG9", "version": 1, "library": { "type": "group", "id": 5316, "name": "Japanese-English Web Parallel Corpus", "links": { "alternate": { "href": "https://www.zotero.org/groups/japanese-english_web_parallel_corpus", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/5316/items/B69PTRG9", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/japanese-english_web_parallel_corpus/items/B69PTRG9", "type": "text/html" } }, "meta": { "createdByUser": { "id": 45026, "username": "ceekz", "name": "Mitsuo Yoshida", "links": { "alternate": { "href": "https://www.zotero.org/ceekz", "type": "text/html" } } }, "creatorSummary": "Schwenk et al.", "parsedDate": "2009-03", "numChildren": 0 }, "data": { "key": "B69PTRG9", "version": 1, "itemType": "conferencePaper", "title": "SMT and SPE Machine Translation Systems for WMT'09", "creators": [ { "creatorType": "author", "firstName": "Holger", "lastName": "Schwenk" }, { "creatorType": "author", "firstName": "Sadaf", "lastName": "Abdul Rauf" }, { "creatorType": "author", "firstName": "Loic", "lastName": "Barrault" }, { "creatorType": "author", "firstName": "Jean", "lastName": "Senellart" } ], "abstractNote": "", "proceedingsTitle": "Proceedings of the Fourth Workshop on Statistical Machine Translation", "conferenceName": "", "publisher": "Association for Computational Linguistics", "place": "Athens, Greece", "date": "March 2009", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "130–134", "series": "", "seriesNumber": "", "DOI": "", "ISBN": "", "citationKey": "", "url": "http://www.statmt.org/wmt09/pdf/WMT-0923.pdf", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2009-10-02T10:05:56Z", "dateModified": "2009-10-09T13:32:57Z" } }, { "key": "XPAPIV5Z", "version": 1, "library": { "type": "group", "id": 5316, "name": "Japanese-English Web Parallel Corpus", "links": { "alternate": { "href": "https://www.zotero.org/groups/japanese-english_web_parallel_corpus", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/5316/items/XPAPIV5Z", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/japanese-english_web_parallel_corpus/items/XPAPIV5Z", "type": "text/html" } }, "meta": { "createdByUser": { "id": 45026, "username": "ceekz", "name": "Mitsuo Yoshida", "links": { "alternate": { "href": "https://www.zotero.org/ceekz", "type": "text/html" } } }, "creatorSummary": "内山 and 井佐", "parsedDate": "2003", "numChildren": 0 }, "data": { "key": "XPAPIV5Z", "version": 1, "itemType": "journalArticle", "title": "日英新聞の記事および文を対応付けるための高信頼性尺度", "creators": [ { "creatorType": "author", "firstName": "将夫", "lastName": "内山" }, { "creatorType": "author", "firstName": "原均", "lastName": "井佐" } ], "abstractNote": "", "publicationTitle": "自然言語処理", "publisher": "", "place": "", "date": "2003", "volume": "10", "issue": "4", "section": "", "partNumber": "", "partTitle": "", "pages": "201-220", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "", "url": "http://mastarpj.nict.go.jp/~mutiyama/pdf/align-ja.pdf", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "ja", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2009-09-30T14:24:35Z", "dateModified": "2009-09-30T14:24:35Z" } }, { "key": "X362FHXM", "version": 1, "library": { "type": "group", "id": 5316, "name": "Japanese-English Web Parallel Corpus", "links": { "alternate": { "href": "https://www.zotero.org/groups/japanese-english_web_parallel_corpus", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/5316/items/X362FHXM", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/japanese-english_web_parallel_corpus/items/X362FHXM", "type": "text/html" } }, "meta": { "createdByUser": { "id": 45026, "username": "ceekz", "name": "Mitsuo Yoshida", "links": { "alternate": { "href": "https://www.zotero.org/ceekz", "type": "text/html" } } }, "creatorSummary": "石坂 et al.", "parsedDate": "2009-05-14", "numChildren": 0 }, "data": { "key": "X362FHXM", "version": 1, "itemType": "journalArticle", "title": "大規模オープンソース日英対訳コーパスの構築", "creators": [ { "creatorType": "author", "firstName": "達也", "lastName": "石坂" }, { "creatorType": "author", "firstName": "将夫", "lastName": "内山" }, { "creatorType": "author", "firstName": "英一郎", "lastName": "隅田" }, { "creatorType": "author", "firstName": "和英", "lastName": "山本" } ], "abstractNote": "Web上の翻訳文書と原文書を収集し，文の対応付けを行うことで日英対訳コーパスを構築した．対訳コーパスは主にオープンソースソフトウェアのマニュアルの文で構成されており，対訳文の総数は約50万文となった．オープンソースな日英対訳コーパスとしては最大級である．この日英対訳コーパスを学習データに使用し，翻訳実験を行った．その結果，BLEU値は最大で44.36となった．この日英対訳コーパスは公開する予定である．\n\nWe built a Japanese-English parallel corpus which collected open source manual in the Web. The parallel corpus is constructed mainly sentences of open source software manuals. The corpus contains about 500,000 sentence pairs that were aligned automatically. It's one of the largest open source Japanese-English parallel corpus. We conducted machine translation (MT) experiments. Maximum BLEU score was 44.36. We will publish the parallel corpus.", "publicationTitle": "情報処理学会研究報告. 自然言語処理研究会報告", "publisher": "", "place": "", "date": "2009-05-14", "volume": "2009-NL-191", "issue": "17", "section": "", "partNumber": "", "partTitle": "", "pages": "1-6", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "", "url": "http://mastarpj.nict.go.jp/~mutiyama/pdf/NL191SLP76-17.pdf", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "ja", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2009-09-30T14:24:35Z", "dateModified": "2009-09-30T14:24:35Z" } }, { "key": "UGJ6CPXX", "version": 1, "library": { "type": "group", "id": 5316, "name": "Japanese-English Web Parallel Corpus", "links": { "alternate": { "href": "https://www.zotero.org/groups/japanese-english_web_parallel_corpus", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/5316/items/UGJ6CPXX", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/japanese-english_web_parallel_corpus/items/UGJ6CPXX", "type": "text/html" } }, "meta": { "createdByUser": { "id": 45026, "username": "ceekz", "name": "Mitsuo Yoshida", "links": { "alternate": { "href": "https://www.zotero.org/ceekz", "type": "text/html" } } }, "creatorSummary": "品川 et al.", "parsedDate": "2006-03", "numChildren": 0 }, "data": { "key": "UGJ6CPXX", "version": 1, "itemType": "conferencePaper", "title": "オンライン対訳文書対からのテキスト領域抽出とアライメント", "creators": [ { "creatorType": "author", "firstName": "哲也", "lastName": "品川" }, { "creatorType": "author", "firstName": "辰則", "lastName": "森" }, { "creatorType": "author", "firstName": "峡", "lastName": "影浦" } ], "abstractNote": "", "proceedingsTitle": "言語処理学会第12回年次大会発表論文集", "conferenceName": "言語処理学会", "publisher": "", "place": "", "date": "2006-03", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "520-523", "series": "", "seriesNumber": "", "DOI": "", "ISBN": "", "citationKey": "", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2009-09-30T14:24:35Z", "dateModified": "2009-09-30T14:24:35Z" } }, { "key": "TWJPMCHI", "version": 1, "library": { "type": "group", "id": 5316, "name": "Japanese-English Web Parallel Corpus", "links": { "alternate": { "href": "https://www.zotero.org/groups/japanese-english_web_parallel_corpus", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/5316/items/TWJPMCHI", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/japanese-english_web_parallel_corpus/items/TWJPMCHI", "type": "text/html" } }, "meta": { "createdByUser": { "id": 45026, "username": "ceekz", "name": "Mitsuo Yoshida", "links": { "alternate": { "href": "https://www.zotero.org/ceekz", "type": "text/html" } } }, "creatorSummary": "淺利 et al.", "parsedDate": "2009-03", "numChildren": 0 }, "data": { "key": "TWJPMCHI", "version": 1, "itemType": "conferencePaper", "title": "Web上の兄弟ページを利用した対訳文書からの段落アラインメント", "creators": [ { "creatorType": "author", "firstName": "俊介", "lastName": "淺利" }, { "creatorType": "author", "firstName": "孔一", "lastName": "竹内" }, { "creatorType": "author", "firstName": "川武", "lastName": "阿辺" }, { "creatorType": "author", "firstName": "峡", "lastName": "影浦" } ], "abstractNote": "", "proceedingsTitle": "言語処理学会第15回年次大会発表論文集", "conferenceName": "言語処理学会", "publisher": "", "place": "", "date": "2009-03", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "869-872", "series": "", "seriesNumber": "", "DOI": "", "ISBN": "", "citationKey": "", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "ja", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2009-09-30T14:24:35Z", "dateModified": "2009-09-30T14:24:35Z" } }, { "key": "B74QTZ47", "version": 1, "library": { "type": "group", "id": 5316, "name": "Japanese-English Web Parallel Corpus", "links": { "alternate": { "href": "https://www.zotero.org/groups/japanese-english_web_parallel_corpus", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/5316/items/B74QTZ47", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/japanese-english_web_parallel_corpus/items/B74QTZ47", "type": "text/html" } }, "meta": { "createdByUser": { "id": 45026, "username": "ceekz", "name": "Mitsuo Yoshida", "links": { "alternate": { "href": "https://www.zotero.org/ceekz", "type": "text/html" } } }, "creatorSummary": "淺利 et al.", "parsedDate": "2008-03", "numChildren": 0 }, "data": { "key": "B74QTZ47", "version": 1, "itemType": "conferencePaper", "title": "Web上の既訳文書を対象とした段落アラインメント", "creators": [ { "creatorType": "author", "firstName": "俊介", "lastName": "淺利" }, { "creatorType": "author", "firstName": "孔一", "lastName": "竹内" }, { "creatorType": "author", "firstName": "川武", "lastName": "阿辺" }, { "creatorType": "author", "firstName": "峡", "lastName": "影浦" } ], "abstractNote": "", "proceedingsTitle": "言語処理学会第14回年次大会発表論文集", "conferenceName": "言語処理学会", "publisher": "", "place": "", "date": "2008-03", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "337-340", "series": "", "seriesNumber": "", "DOI": "", "ISBN": "", "citationKey": "", "url": "http://cl.cs.okayama-u.ac.jp/study/data/h20/asari_nlp2008.pdf", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "ja", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2009-09-30T14:24:35Z", "dateModified": "2009-09-30T14:24:35Z" } }, { "key": "2AAPR5ZC", "version": 1, "library": { "type": "group", "id": 5316, "name": "Japanese-English Web Parallel Corpus", "links": { "alternate": { "href": "https://www.zotero.org/groups/japanese-english_web_parallel_corpus", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/5316/items/2AAPR5ZC", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/japanese-english_web_parallel_corpus/items/2AAPR5ZC", "type": "text/html" } }, "meta": { "createdByUser": { "id": 45026, "username": "ceekz", "name": "Mitsuo Yoshida", "links": { "alternate": { "href": "https://www.zotero.org/ceekz", "type": "text/html" } } }, "creatorSummary": "Resnik and Smith", "parsedDate": "2003", "numChildren": 0 }, "data": { "key": "2AAPR5ZC", "version": 1, "itemType": "journalArticle", "title": "The Web as a parallel corpus", "creators": [ { "creatorType": "author", "firstName": "Philip", "lastName": "Resnik" }, { "creatorType": "author", "firstName": "Noah A.", "lastName": "Smith" } ], "abstractNote": "Parallel corpora have become an essential resource for work in multilingual natural language processing. In this article, we report on our work using the STRAND system for mining parallel text on the World Wide Web,first reviewing the original algorithm and results and then presenting a set of significant enhancements. These enhancements include the use of supervised learning based on structural features of documents to improve classification performance, a new content-based measure of translational equivalence, and adaptation of the system to take advantage of the Internet Archive for mining parallel text from the Web on a large scale. Finally, the value of these techniques is demonstrated in the construction of a significant parallel corpus for a low-density language pair.", "publicationTitle": "Comput. Linguist.", "publisher": "", "place": "", "date": "2003", "volume": "29", "issue": "3", "section": "", "partNumber": "", "partTitle": "", "pages": "349-380", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "", "url": "http://portal.acm.org/citation.cfm?id=964753", "accessDate": "2009-09-30T14:20:28Z", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ACM", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2009-09-30T14:24:35Z", "dateModified": "2009-09-30T14:24:35Z" } } ]