Information retrieval using word senses

Abstract

Information retrieval using word senses is emerging as a good research challenge on semantic information retrieval. In this paper, we propose a new method using word senses in information retrieval: root sense tagging method. This method assigns coarse-grained word senses defined in WordNet to query terms and document terms by unsupervised way using co-occurrence information constructed automatically. Our sense tagger is crude, but performs consistent disambiguation by considering only the single most informative word as evidence to disambiguate the target word. We also allow multiple-sense assignment to alleviate the problem caused by incorrect disambiguation.Experimental results on a large-scale TREC collection show that our approach to improve retrieval effectiveness is successful, while most of the previous work failed to improve performances even on small text collection. Our method also shows promising results when is combined with pseudo relevance feedback and state-of-the-art retrieval function such as BM25.

Analysis of Word Sense Disambiguation-Based Information Retrieval

“…In fact, even though the main objective of their study was to evaluate the performance of WSD in IR, they should have examined the accuracy of their disambiguation method in isolation, so that they could quantify its effect when used in their IR experiments. A more comprehensive study was carried out in [9], in which the authors added additional sense information to both documents and queries using WordNet. Their large-scale experiments on a TREC collection produced promising results, clearly demonstrating the positive effect of WSD on retrieval performances.…”

An Ontology-based Approach to Text Latent Semantic Domain Recognition

“…Because this mapping not only formalize thetext message [7]- [10], but also provides other algorithms with a formal basis to process the text and its message according to the knowledge formalized in the ontology [1], [11], [12]. Regardless of secondary processing, the main purpose of the matching document to lexical resources is to solve the problem of natural language ambiguity [9], [10], [13].…”

Comparison of Application Effect of Natural Language Processing Techniques for Information Retrieval

“…They only considered the 25 most original word meanings of a word in the WordNet and then assigned a meaning to a word, which can insure the accuracy of WSD [17]. Although they did not give the accuracy of disambiguation，the experimental results in TREC7 and TREC8 data showed that the disambiguation method can increase the retrieval effect more than 10 %.…”