首页> 外文会议>International Conference on Applications of Natural Language to Information Systems >Applying Wikipedia's Multilingual Knowledge to Cross—Lingual Question Answering
【24h】

Applying Wikipedia's Multilingual Knowledge to Cross—Lingual Question Answering

机译:将维基百科的多语言知识应用于交叉的问题回答

获取原文

摘要

The application of the multilingual knowledge encoded in Wikipedia to an open-domain Cross-Lingual Question Answering system based on the Inter Lingual Index (ILI) module of Euro WordNet is proposed and evaluated. This strategy overcomes the problems due to ILI's low coverage on proper nouns (Named Entities). Moreover, as these are open class words (highly changing), using a community-based up-to-date resource avoids the tedious maintenance of hand-coded bilingual dictionaries. A study reveals the importance to translate Named Entities in CL-QA and the advantages of relying on Wikipedia over ILI for doing this. Tests on questions from the Cross-Language Evaluation Forum (CLEF) justify our approach (20% of these are correctly answered thanks to Wikipedia's Multilingual Knowledge).
机译:提出了基于欧洲WordNet的思想索引(ILI)模块的Wikipedia中编码的多语言知识在Wikipedia中的应用,并评估了欧式Wordnet的思想索引模块。该策略克服了Ili对适当名词(命名实体)的低覆盖率的问题。此外,由于这些是开放类词(高度变化),使用基于社区的最新资源避免了繁琐的手工编码双语词典的维护。一项研究揭示了在CL-QA中翻译命名实体的重要性以及依靠Wikipedia在Ili上进行这样做的优势。关于跨语言评估论坛(谱号)的问题的测试证明了我们的方法(其中20%的20%是正确回答的,因为维基百科的多语言知识)。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号