问答服务中的问题检索任务研究

Research on Question Retrieval Task in Community-based Q&A Service

"新浪爱问"和"百度知道"等问答服务在近年来得到快速发展,并积累了大量的问答对数据。问答服务系统的一个重要功能是问题检索,即根据用户的提问,在已有的问答对数据中查找与用户提问主题相关的其他问题,以帮助用户获取需要的信息。在语言模型框架下提出一个计算问题间的主题相关性的方法。通过在真实问答对数据上进行实验,表明笔者的方法可以有效的检索到主题相关的问题,其性能优于传统的计算方法。

Community-based QA service such as Sina iask and Baidu Zhidao already build up large archives of questions and answers.In QA service,question retrieval is one of the major tasks.It means finding questions in the archive that are semantically relevance with a user＇s question that can satisfy the users＇ need.In this paper,we discuss how to find similar questions based on their topics.The experiment results show that with our approach it is possible to find topic relevant questions.And our approach outperforms traditional approach.