Mining Wikipedia Resources for Discovering Answers to List Questions in Web Snippets

摘要

This paper presents LiSnQA, a list question answering system that extracts answers to list queries from the short descriptions of web-sites returned by search engines, called web snippets. LiSnQA mines Wikipedia resources in order to obtain valuable information that assists in the extraction of these answers. The interesting facet of LiSnQA is, that in contrast to current systems, it does not account for lists in Wikipedia, but for its redirections, categories, sandboxes, and first definition sentences. Results show that these resources strengthen the answering process.