Database清华大学ResearchGroupTsinghua UniversityAn Effective Approach for Searching ClosestSentence Translations from The WebJu Fan, Guoliang Li, and Lizhu ZhouDatabase Research Group, Tsinghua UniversityDASFAA 2o11-Apr.23, Hong Kong
An Effective Approach for Searching Closest Sentence Translations from The Web Ju Fan, Guoliang Li, and Lizhu Zhou Database Research Group, Tsinghua University DASFAA 2011 – Apr. 23, Hong Kong Database Research Group
Outline Introduction Overview of Our Approach Phrase-Based Similarity ModelPhrase SelectionExperiments· ConclusionSCST@DASFAA2011
Outline • Introduction • Overview of Our Approach • Phrase-Based Similarity Model • Phrase Selection • Experiments • Conclusion SCST@DASFAA 2011
OutlineIntroductionOverview of Our ApproachPhrase-Based Similarity ModelPhraseSelectionExperimentsConclusionSCST@DASFAA2011
Outline • Introduction • Overview of Our Approach • Phrase-Based Similarity Model • Phrase Selection • Experiments • Conclusion SCST@DASFAA 2011
Background: Parallel sentences on the Web? Sentences with the well-translated counterpart: An English-to-Chinese ExampleObama said hehopes to get Congress toapprove it next year奥巴马总统说他争取让希望国会明年批准该协议A rich source for translation: Commercial Systems有道SOSO词典youdaoDict.cn词典SCST@DASFAA2011
Background • Parallel sentences on the Web ▪ Sentences with the well-translated counterpart ▪ An English-to-Chinese Example • A rich source for translation • Commercial Systems SCST@DASFAA 2011 Obama said he hopes to get Congress to approve it next year 奥巴马总统说他争取让希望国会明年批准该协议
BackgroundSentence-Level Translation AidSen 1 (E-Sentence MatchingSen2(E-C)Sen3 (E-C)ResearchIssueRatiaHelSentencesfective'similarity model between sentences (inhifriceopdnguage (e.g., English sentences)C)结果很好ParallelSentenceClosestSentencesDatabasewithTranslationParallelSentenceDiscoveryandExtractionWebSCST@DASFAA2011
Parallel Sentences E.g., The result is good 结果很好 Background SCST@DASFAA 2011 Parallel Sentence Database Sen 1 (EC) Sen2 (E-C) Sen3 (E-C) sen n (EC) . Closest Sentences with Translation Query Sentence (English) Web Parallel Sentence Discovery and Extraction Sentence-Level Translation Aid Sentence Matching An effective similarity model between sentences in the source language (e.g., English sentences) Research Issue