Looking Under the Hood : Tools for Diagnosing your Question Answering Engine

Simple item page
dc.creatorBreck, Eric
dc.creatorLight, Marc
dc.creatorMann, Gideon S.
dc.creatorRiloff, Ellen
dc.creatorAnand, Brianne Brown Pranav
dc.creatorRooth, Mats
dc.creatorThelen, Michael
dc.date2001-07-03
dc.date.accessioned2026-07-07T03:17:19Z
dc.date.available2026-07-07T03:17:19Z
dc.descriptionIn this paper we analyze two question answering tasks : the TREC-8 question answering task and a set of reading comprehension exams. First, we show that Q/A systems perform better when there are multiple answer opportunities per question. Next, we analyze common approaches to two subproblems: term overlap for answer sentence identification, and answer typing for short answer extraction. We present general tools for analyzing the strengths and limitations of techniques for these subproblems. Our results quantify the limitations of both term overlap and answer typing to distinguish between competing answer candidates.
dc.descriptionRevision of paper appearing in the Proceedings of the Workshop on Open-Domain Question Answering
dc.identifierhttps://arxiv.org/abs/cs/0107006
dc.identifierhttp://arxiv.org/abs/cs/0107006
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/30679
dc.subjectComputation and Language
dc.subjectI.2.7
dc.titleLooking Under the Hood : Tools for Diagnosing your Question Answering Engine
dc.typetext

Files

Collections

arXiv