A Question Answering System Supported by Information Extraction

A Question Answering System Supported by Information Extraction* Rohini Srihari Cymfony Inc. 5500 Main Street Williamsville, NY 14221 rohini@cymfony.com Wei Li Cymfony Inc. 5500 Main Street Williamsville, NY14221 wei@cymfony.com Abstract This paper discusses an information extraction (IE) system, Textract, in natural language (NL) question answering (QA) and examines the role of IE in QA application. It shows: (i) Named Entity tagging is an important component for QA, (ii) an NL shallow parser provides a structural basis for questions, and (iii) high-level domain independent IE can result in a QA breakthrough. Introduction With the explosion of information in Internet, Natural language QA is recognized as a capability with great potential. Traditionally, QA has attracted many AI researchers, but most QA systems developed are toy systems or games confined to lab and a very restricted domain. More recently, Text Retrieval Conference (TREC-8) designed a QA track to stimulate the research for real world application. Due to little linguistic support from text analysis, conventional IR systems or search engines do not really perform the task of information retrieval; they in fact aim at only document retrieval. The following quote from the QA Track Specifications (www.research.att.com/ -singhal/qa-track-spec.txt) in the TREC community illustrates this point. Current information retrieval systems allow us to locate documents that might contain the pertinent information, but most of them leave it to the user to extract the useful information from a ranked list. This leaves the (often unwilling) user with a relatively large amount of text to consume. There is an urgent need for tools that would reduce the amount of text one might have to read in order to obtain the desired information. This track aims at doing exactly that for a special (and popular) class of information seeking behavior: QUESTION ANSWERING. People have questions and they need answers, not documents. Automatic question answering will definitely be a significant advance in the state-of-art information retrieval technology. Kupiec (1993) presented a QA system MURAX using an on-line encyclopedia. This system used the technology of robust shallow parsing but suffered from the lack of basic information extraction support. In fact, the most siginifcant IE advance, namely the NE (Named Entity) technology, occured after Kupiec (1993), thanks to the MUC program (MUC-7 1998). High-level IE technology beyond NE has not been in the stage of possible application until recently. AskJeeves launched a QA portal (www.askjeeves.com). It is equipped with a fairly sophisticated natural language question parser, but it does not provide direct answers to the asked questions. Instead, it directs the user to the relevant web pages, just as the traditional search engine does. In this sense, AskJeeves has only done half of the job for QA. We believe that QA is an ideal test bed for demonstrating the power of IE. There is a natural co-operation between IE and IR; we regard QA as one major intelligence which IE can offer IR. * This work was supported in part by the SBIR grants F30602-98-C-0043 and F30602-99-C-0102 from Air Force Research Laboratory …

Content truncated to 500 words