跨语言信息检索技术.pptxVIP

Cross Language Information Retrieval;Road Map;2020-03-01;2020-03-01;;2020-03-01;Usage of content languages for websites;Cross Language IR;Why do we need CLIR systems?;General Issues With CLIR;Matching strategies;Cognate matching(同源匹配）;2020-03-01;2020-03-01;2020-03-01;2020-03-01;2020-03-01;2020-03-01;2020-03-01;Interlingual approach;Translation techniques;Dictionary-based methods;2020-03-01;2020-03-01;2020-03-01;2020-03-01;2020-03-01;2020-03-01;2020-03-01;2020-03-01;2020-03-01;2020-03-01;2020-03-01;2020-03-01;The WWW can provide rich and ubiquitous machine-readable resources, from which we may be able to automatically extract information useful for CLIR. For example, Chen (2002) and Chen and Gey (2003) made use of a general search engine on the Internet and tried to find English translation equivalents of Chinese or Japanese terms (mainly proper nouns) by analyzing contexts of these terms in Chinese and Japanese Web documents returned by the engine.;2020-03-01;Use of part-of-speech tags;Parallel corpus-based disambiguation;2020-03-01;Disambiguation based on co-occurrence statistics;Query expansion for disambiguation;Pre-translation feedback;Post-translation feedback;bi-directional translation;2020-03-01;2020-03-01;47;2020-03-01;2020-03-01;2020-03-01;2020-03-01;2020-03-01;2020-03-01;2020-03-01;2.2 数字图书馆的跨语言检索;WorldWideScience/multilingual;WorldWideScience/multilingual;2.3 跨语言专利检索;2010年5月，世界知识产权组织WIPO发布了跨语言专利检索系统PATENTSCOPE的测试版，标志着跨语言信息检索在专利检索中的应用从实验室走向实用化。 该系统只能提供英语、法语、德语、日语、西班牙语5种语言之间的跨语言专利检索。;;;2.4 跨语言图像检索;;;2.5 电子商务中的应用;2020-03-01;;Reference;2020-03-01;2020-03-01;2020-03-01;2020-03-01;2020-03-01;2020-03-01;2020-03-01;2020-03-01;2020-03-01;2020-03-01