Latent semantic indexing (LSI) fails for TREC collections
Authors:
Open Access
- 31 March 2011
- journal article
- Published by Association for Computing Machinery (ACM) in ACM SIGKDD Explorations Newsletter
- Vol. 12 (2) , 5-10
Abstract
The aim of latent semantic indexing (LSI) is to uncover the relationships between terms, hidden concepts, and documents. LSI uses the matrix factorization technique known as singular value decomposition (SVD). In this paper, we apply LSI to standard benchmark collections. We find that LSI yields poor retrieval accuracy on the TREC 2, 7, 8, and 2004 collections. We believe that the negative result is robust, because we try more LSI variants than any previous work. First, we show that using Okapi BM25 weights for terms in documents improves the performance of LSI. Second, we derive novel scoring methods that implement the ideas of query expansion and score regularization in the LSI framework. Third, we show how to combine the BM25 method with LSI methods. All proposed methods are evaluated experimentally on the four TREC collections mentioned above. The experiments show that the new variants of LSI improve upon previous LSI methods. Nevertheless, no way of using LSI achieves a worthwhile improvement in retrieval accuracy over BM25.Keywords
This publication has 10 references indexed in Scilit:
- Improvements that don't add up2009
- Straightforward Feature Selection for Scalable Latent Semantic Indexing2009
- An empirical study of required dimensionality for large-scale latent semantic indexing applications2008
- Score standardization for inter-collection comparison of retrieval systems2008
- Essential Dimensions of Latent Semantic Indexing (LSI)2007
- Regularizing ad hoc retrieval scores2005
- Term norm distribution and its effects on Latent Semantic IndexingInformation Processing & Management, 2005
- Evaluating evaluation measure stability2000
- Fusion Via a Linear Combination of ScoresInformation Retrieval Journal, 1999
- Indexing by latent semantic analysisJournal of the American Society for Information Science, 1990