Semantic term matching in axiomatic approaches to information retrieval
H. Fang, and C. Zhai. SIGIR '06: Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval, page 115--122. New York, NY, USA, ACM Press, (2006)
DOI: http://dx.doi.org/10.1145/1148170.1148193
Abstract
A common limitation of many retrieval models, including the recently proposed axiomatic approaches, is that retrieval scores are solely based on exact (i.e., syntactic) matching of terms in the queries and documents, without allowing distinct but semantically related terms to match each other and contribute to the retrieval score. In this paper, we show that semantic term matching can be naturally incorporated into the axiomatic retrieval model through defining the primitive weighting function based on a semantic similarity function of terms. We define several desirable retrieval constraints for semantic term matching and use such constraints to extend the axiomatic model to directly support semantic term matching based on the mutual information of terms computed on some document set. We show that such extension can be efficiently implemented as query expansion. Experiment results on several representative data sets show that, with mutual information computed over the documents in either the target collection for retrieval or an external collection such as the Web, our semantic expansion consistently and substantially improves retrieval accuracy over the baseline axiomatic retrieval model. As a pseudo feedback method, our method also outperforms a state-of-the-art language modeling feedback method.
SIGIR '06: Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval
year
2006
pages
115--122
publisher
ACM Press
posted-at
2007-02-16 16:51:31
citeulike-article-id
1109915
priority
2
isbn
1595933697
comment
== Based on the axiomatic (functional) retrieval models.
== Incorporates semantic term matching to the retrieval function.
== Shows that this is equivalent to a semantic query expansion.
%0 Conference Paper
%1 Fang2006Semantic
%A Fang, Hui
%A Zhai, Chengxiang
%B SIGIR '06: Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval
%C New York, NY, USA
%D 2006
%I ACM Press
%K ir semantic term_matching
%P 115--122
%R http://dx.doi.org/10.1145/1148170.1148193
%T Semantic term matching in axiomatic approaches to information retrieval
%U http://dx.doi.org/10.1145/1148170.1148193
%X A common limitation of many retrieval models, including the recently proposed axiomatic approaches, is that retrieval scores are solely based on exact (i.e., syntactic) matching of terms in the queries and documents, without allowing distinct but semantically related terms to match each other and contribute to the retrieval score. In this paper, we show that semantic term matching can be naturally incorporated into the axiomatic retrieval model through defining the primitive weighting function based on a semantic similarity function of terms. We define several desirable retrieval constraints for semantic term matching and use such constraints to extend the axiomatic model to directly support semantic term matching based on the mutual information of terms computed on some document set. We show that such extension can be efficiently implemented as query expansion. Experiment results on several representative data sets show that, with mutual information computed over the documents in either the target collection for retrieval or an external collection such as the Web, our semantic expansion consistently and substantially improves retrieval accuracy over the baseline axiomatic retrieval model. As a pseudo feedback method, our method also outperforms a state-of-the-art language modeling feedback method.
%@ 1595933697
@inproceedings{Fang2006Semantic,
abstract = {A common limitation of many retrieval models, including the recently proposed axiomatic approaches, is that retrieval scores are solely based on exact (i.e., syntactic) matching of terms in the queries and documents, without allowing distinct but semantically related terms to match each other and contribute to the retrieval score. In this paper, we show that semantic term matching can be naturally incorporated into the axiomatic retrieval model through defining the primitive weighting function based on a semantic similarity function of terms. We define several desirable retrieval constraints for semantic term matching and use such constraints to extend the axiomatic model to directly support semantic term matching based on the mutual information of terms computed on some document set. We show that such extension can be efficiently implemented as query expansion. Experiment results on several representative data sets show that, with mutual information computed over the documents in either the target collection for retrieval or an external collection such as the Web, our semantic expansion consistently and substantially improves retrieval accuracy over the baseline axiomatic retrieval model. As a pseudo feedback method, our method also outperforms a state-of-the-art language modeling feedback method.},
added-at = {2009-03-16T12:06:11.000+0100},
address = {New York, NY, USA},
author = {Fang, Hui and Zhai, Chengxiang},
biburl = {https://www.bibsonomy.org/bibtex/22dc6f91ae0375071e5d843af53e0bb80/davidlan},
booktitle = {SIGIR '06: Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval},
citeulike-article-id = {1109915},
comment = {== Based on the axiomatic (functional) retrieval models.
== Incorporates semantic term matching to the retrieval function.
== Shows that this is equivalent to a semantic query expansion.},
doi = {http://dx.doi.org/10.1145/1148170.1148193},
interhash = {4291d676f1cadfb1d17db43685d55517},
intrahash = {2dc6f91ae0375071e5d843af53e0bb80},
isbn = {1595933697},
keywords = {ir semantic term_matching},
pages = {115--122},
posted-at = {2007-02-16 16:51:31},
priority = {2},
publisher = {ACM Press},
timestamp = {2009-03-16T12:06:11.000+0100},
title = {Semantic term matching in axiomatic approaches to information retrieval},
url = {http://dx.doi.org/10.1145/1148170.1148193},
year = 2006
}