利用知识本体链解决跨语言资讯检索中翻译歧义性的问题.pptVIP

利用知識本體鏈解決跨語言資訊檢索中翻譯歧義性的問題Resolving Translation Ambiguity using Ontological Chains for Cross Language Information Retrieval Institute of Computer and Information Science National Chiao Tung University Student: Je-Wei Liang Advisor: Dr. Hao-Ren Ke Dr. Wei-Pang Yang Outline Introduction Related Work Query Translation Word Sense Disambiguation Ontology-based CLIR Query Translation Resolving Translation Ambiguity Mono-lingual IR Evaluation Document set Topics Relevance Assessment Result Conclusion Reference Introduction: What is Cross Language Information Retrieval? Introduction: Why CLIR ? Introduction: Ambiguity Motivation and Objectives Motivation Queries are usually short. e.g. 魚 A word may have many possible translations. e.g. 男人: man, gentleman Lack of domain knowledge e.g. ‘galleries’ is related to ‘library’ Objectives Design an ontology-based CLIR System Query expansion using WordNet. Resolving translation ambiguity using ontological chains. Related Work Related Work: Improved use of Contextual Information in CLIR [Fung98] Related Work: WSD using Lexical Chain [Barzilay97] WSD using Lexical Chain [Barzilay97] WSD using Lexical Chain [Barzilay97] WSD using Lexical Chain [Barzilay97] Related Work: Building a Chinese English WordNet [Chen02] Related Work: Building a Chinese English WordNet [Chen02] Advantages and Disadvantages of Related Work System workflow Query Translation Query Translation Query Translation: An Example The query ‘魚’ is translated to ‘fish’, and retrieves the following documents by looking up WordNet. Query Translation: Translation Ambiguity Resolving Translation Ambiguity Ontology Construction Each ImageCLEF2004 document belongs to one or more categories. There are 946 distinct categories. Human experts gather related categories to form a hierarchy. E.g. ‘fish processing’ and ‘fisherman’ are assigned to the parent node ‘漁業’. Keyword Extraction Ontology Node Representation Each node is represented by the term-to-conc