Learning Transfer Rules from Annotated English - Vietnamese Bilingual Corpus

• Item type: SIG Technical Reports(1)
• 公開日: 2004-12-04
• タイトル: Learning Transfer Rules from Annotated English - Vietnamese Bilingual Corpus
• タイトル / 言語: en
• タイトル: Learning Transfer Rules from Annotated English - Vietnamese Bilingual Corpus
• 言語: eng
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_18gh
• 資源タイプ: technical report
• 著者所属: Faculty of Information Technology University of Natural Sciences VNU - HCMC
• 著者所属: Center of Information Technology Development Vietnam National University of HCMC
• 著者所属(英): en
• 著者所属(英): Faculty of Information Technology, University of Natural Sciences, VNU - HCMC
• 著者所属(英): en
• 著者所属(英): Center of Information Technology Development, Vietnam National University of HCMC
• 著者名: Dinh, Dien; Hoang, Kiem
• 著者名(英): Dinh, Dien; Hoang, Kiem
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: Due to the difference of language typology many transfer rules are required in the lexical and structural transfer stage in the English-to-Vietnamese Machine Translation. Recently many NLP (Natural Language Processing) tasks have changed from rule-based approaches into corpus-based approaches with large annotated corpora. Corpus-based NLP tasks for such popular languages as English French etc. have been well studied with satisfactory achievements. In contrast corpus-based NLP tasks for Vietnamese are at a deadlock due to absence of annotated training data. Furthermore hand-annotation of even reasonably well-determined features such as part-of-speech (POS) tags has proved to be labor intensive and costly. In this paper we present issues of collection and annotation (Word Alignment. Word Segmentation Vietnamese and Part-of-Speech) of a parallel corpus of English-Vietnamese named EVC (English-Vietnamese Corpus). From this EVC transfer rules have been automatically mined to train for Vietnamese-related NLP tasks and to study English - Vietnamese comparative linguistics.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: Due to the difference of language typology, many transfer rules are required in the lexical and structural transfer stage in the English-to-Vietnamese Machine Translation. Recently, many NLP (Natural Language Processing) tasks have changed from rule-based approaches into corpus-based approaches with large annotated corpora. Corpus-based NLP tasks for such popular languages as English, French, etc. have been well studied with satisfactory achievements. In contrast, corpus-based NLP tasks for Vietnamese are at a deadlock due to absence of annotated training data. Furthermore, hand-annotation of even reasonably well-determined features such as part-of-speech (POS) tags has proved to be labor intensive and costly. In this paper, we present issues of collection and annotation (Word Alignment. Word Segmentation Vietnamese and Part-of-Speech) of a parallel corpus of English-Vietnamese named EVC (English-Vietnamese Corpus). From this EVC transfer rules have been automatically mined to train for Vietnamese-related NLP tasks and to study English - Vietnamese comparative linguistics.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AA11135936
• 書誌情報: 情報処理学会研究報告知能と複雑系（ICS）; 巻 2004, 号 125(2004-ICS-138), p. 31-36, 発行日 2004-12-04
• Notice: SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc.
• 出版者 / 言語: ja
• 出版者: 情報処理学会