Beyond keywords: Automated question answering on the web

Abstract

Online advertising portal Ask.com has introduced a completely automated open-domain question answering (QA) on the Web, to locate, extract, and provide specific answers to user questions expressed in natural language. The distinctions of QA from fixed closed domain include existence of simpler variants, expectations of context, and speed. ASU QA matches the question to one of the trained regular expressions, while NSIR and ASU QA uses only a few grammatical and semantic categories and fine-tuned taxonomies. QA is also able to locate potentially malevolent online content, helping law-enforcement and public oversight groups combat the proliferation of materials that threaten cybersecurity or promote terrorism. Various objectives of Web QA systems include increasing traffic volume and visibility online to generate maximum potential advertising and demonstrating innovative ideas in certain unexplored fields of research.