Type-Based Query Expansion for Sentence Retrieval

Authors:
Keke Cai;Chun Chen;Jiajun Bu;Guang Qiu
Affiliations:
College of Computer Science, Zhejiang University, Hangzhou, 310027, China;College of Computer Science, Zhejiang University, Hangzhou, 310027, China;College of Computer Science, Zhejiang University, Hangzhou, 310027, China;College of Computer Science, Zhejiang University, Hangzhou, 310027, China
Venue:
ICCS '07 Proceedings of the 7th international conference on Computational Science, Part I: ICCS 2007
Year:
2007

Citing 6
Cited 0

Automatic structuring and retrieval of large text files

Communications of the ACM
Retrieval and novelty detection at the sentence level

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

Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval
Using top-ranking sentences to facilitate effective information access: Book Reviews

Journal of the American Society for Information Science and Technology
Novelty detection based on sentence level patterns

Proceedings of the 14th ACM international conference on Information and knowledge management
Bayesian query-focused summarization

ACL-44 Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, a novel sentence retrieval model with type-based expansion is proposed. In this retrieval model, sentences expected to be relevant should meet with the requirements both in query terms and query types. To obtain the information about query types, this paper proposes a solution based on classification, which utilizes the potential associations between terms and information types to obtain the optimized classification results. Inspired by the idea that relevant sentences always tend to occur nearby, this paper further re-ranks each sentence by considering the relevance of its adjacent sentences. The proposed retrieval model has been compared with other traditional retrieval models and experiment results indicate its significant improvements in retrieval effectiveness.