LBSC 796INFM 718R Week 12Question Answering.ppt

LBSC 796/INFM 718R: Week 12Question Answering Jimmy Lin College of Information Studies University of Maryland Monday, April 24, 2006 The Information Retrieval Cycle Question Answering Information Seeking Behavior Potentially difficult or time-consuming steps of the information seeking process: Query formulation Query refinement Document examination and selection What if a system can directly satisfy information needs phrased in natural language? Question asking is intuitive for humans Compromised query = formalized query When is QA a good idea? Question asking is effective when… The user knows exactly what he or she wants The desired information is short, fact-based, and (generally) context-free Question asking is less effective when… The information need is vague or broad The information request is exploratory in nature Contrasting Information Needs Ad hoc retrieval: find me documents “like this” Question answering From this… To this… Why is this better than Google? Keywords cannot capture semantic constraints between query terms: Document retrieval systems cannot fuse together information from multiple documents Who would benefit? Sample target users of a QA system Question answering fills an important niche in the broader information seeking environment Roots of Question Answering Information Retrieval (IR) Information Extraction (IE) Information Retrieval (IR) Can substitute “document” for “information” IR systems Use statistical methods Rely on frequency of words in query, document, collection Retrieve complete documents Return ranked lists of “hits” based on relevance Limitations Answers questions indirectly Does not attempt to understand the “meaning” of user’s query or documents in the collection Information Extraction (IE) IE systems Identify documents of a specific type Extract information according to pre-defined templates Place the information into frame-like database records Templates = pre-defined questions Extracted infor