In 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.
@article{arxiv.cs/0107006,
title = {Looking Under the Hood : Tools for Diagnosing your Question Answering Engine},
author = {Eric Breck and Marc Light and Gideon S. Mann and Ellen Riloff and Brianne Brown Pranav Anand and Mats Rooth and Michael Thelen},
journal= {arXiv preprint arXiv:cs/0107006},
year = {2007}
}
Comments
Revision of paper appearing in the Proceedings of the Workshop on Open-Domain Question Answering