机构地区: 华中师范大学信息管理系
出 处: 《图书情报知识》 2010年第3期51-61,共11页
摘 要: 将自然语言处理技术——统计语言模型引入信息检索领域产生了一系列全新的检索模型,典型包括查询似然模型、生成相关性模型、词项依赖模型、统计翻译模型、泊松分布模型以及风险最小化框架等。本文从统计学模型以及N-gram技术的角度重点解析这些信息检索模型的演进过程。最后对基于统计语言模型的信息检索模型的发展过程以及未来发展趋势和挑战进行了总结。 The application of statistical language model, one of the natural larguage processing technologies, in information retrieval has brought about a series of brand-new retrieval models, such as query likelihood model, generative relevance model, item dependence model, statistical translation model, poisson distribution model and risk minimum framework. This article analyzes the evolution of these information retrieval models based on statistical model and N-gram. It also compares the retrieval effects of statistical language model and classic probability model through retrieval experiments. At the end of the article, a conclusion is drawn about the evolution, the trends and challenges of information retrieval model based on statistical language model.
领 域: [文化科学]