NLPX - An XML-IR System with a Natural Language Interface
暂无分享,去创建一个
Traditional information retrieval (IR) systems respond to user queries with ranked lists of relevant documents. The separation of content and structure in XML documents allows individual XML elements to be selected in isolation. Thus, users expect XML-IR systems to return highly relevant results that are more precise than entire documents. This paper presents such a system. The system accepts queries in both natural language (English) and formal XPath-like format (NEXI) and matches to a set of relevant and appropriately-sized elements using an effective ranking scheme.
[1] Eric Brill,et al. A Simple Rule-Based Part of Speech Tagger , 1992, HLT.
[2] Shai Geva,et al. XPath Inverted File for Information Retrieval , 2003 .
[3] Andrew Trotman,et al. The Simplest Query Language That Could Possibly Work , 2004 .
[4] Gabriella Kazai,et al. Overview of the Initiative for the Evaluation of XML retrieval (INEX) 2002 , 2002, INEX Workshop.
[5] Andrew Trotman,et al. Narrowed Extended XPath I (NEXI) , 2004, INEX.