A re-examination of IR techniques in QA system

Authors:
Yi Chang;Hongbo Xu;Shuo Bai
Affiliations:
Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China;Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China;Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China
Venue:
IJCNLP'04 Proceedings of the First international joint conference on Natural Language Processing
Year:
2004

Citing 5
Cited 2

A very fast prototype retrieval system using statistical ranking

ACM SIGIR Forum
A re-examination of text categorization methods

Proceedings of the 22nd annual international ACM SIGIR conference on Research and development in information retrieval
Quantitative evaluation of passage retrieval algorithms for question answering

Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval
Retrieval and novelty detection at the sentence level

Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval
Document retrieval in the context of question answering

ECIR'03 Proceedings of the 25th European conference on IR research

Indexing low frequency information for question answering

Large Scale Semantic Access to Content (Text, Image, Video, and Sound)
Chinese question-answering: comparing monolingual with english-chinese cross-lingual results

AIRS'06 Proceedings of the Third Asia conference on Information Retrieval Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

The performance of Information Retrieval in the Question Answering system is not satisfactory from our experiences in TREC QA Track. In this article, we take a comparative study to re-examine IR techniques on document retrieval and sentence level retrieval respectively. Our study shows: 1) query reformulation should be a necessary step to achieve a better retrieval performance; 2) The techniques for document retrieval are also effective in sentence level retrieval, and single sentence will be the appropriate retrieval granularity.