State-of-the-Art Techniques for Question Analysis

From HLT@INESC-ID

Ana Cristina Mendes

Date

  • 15:00, May 15, 2009
  • Room 336

Speaker

Abstract

Question-Answering (QA) is the task of retrieving the correct and concise answer to questions posed in Natural Language, from large amounts of free-text documents. Being the first step on the typical architecture of QA systems, the analysis of questions plays a crucial role in the success of such systems: on one hand, the question analysis can greatly narrow down the search space by posing constraints to the answer; on the other hand, it is unlikely that a question will be properly answered if this step has performed poorly.

This presentation addresses the techniques employed in question analysis, under two different perspectives: question analysis will be decomposed in sub-tasks, for which the state-of-the-art techniques will be introduced; also, references will be made to question analysis in domains with different characteristics.