2015
Journal Articles
Adrian-Gabriel Chifu; Florentina Hristea; Josiane Mothe; Marius Popescu
Word sense discrimination in information retrieval: A spectral clustering-based approach Journal Article
In: Information Processing & Management, vol. 51, no. 2, pp. 16–31, 2015.
Abstract | Links | BibTeX | Tags: High Precision, Information Retrieval, Spectral Clustering, Word Sense Disambiguation, Word Sense Discrimination
@article{chifu2015word,
title = {Word sense discrimination in information retrieval: A spectral clustering-based approach},
author = {Adrian-Gabriel Chifu and Florentina Hristea and Josiane Mothe and Marius Popescu},
url = {https://hal.archives-ouvertes.fr/hal-01153775/document},
year = {2015},
date = {2015-03-01},
urldate = {2015-01-01},
journal = {Information Processing & Management},
volume = {51},
number = {2},
pages = {16--31},
publisher = {Elsevier},
abstract = {Word sense ambiguity has been identified as a cause of poor precision in information retrieval (IR) systems. Word sense disambiguation and discrimination methods have been defined to help systems choose which documents should be retrieved in relation to an ambiguous query. However, the only approaches that show a genuine benefit for word sense discrimination or disambiguation in IR are generally supervised ones. In this paper we propose a new unsupervised method that uses word sense discrimination in IR. The method we develop is based on spectral clustering and reorders an initially retrieved doc- ument list by boosting documents that are semantically similar to the target query. For several TREC ad hoc collections we show that our method is useful in the case of queries which contain ambiguous terms. We are interested in improving the level of precision after 5, 10 and 30 retrieved documents (P@5, P@10, P@30) respectively. We show that precision can be improved by 8% above current state-of-the-art baselines. We also focus on poor performing queries.},
keywords = {High Precision, Information Retrieval, Spectral Clustering, Word Sense Disambiguation, Word Sense Discrimination},
pubstate = {published},
tppubtype = {article}
}
Word sense ambiguity has been identified as a cause of poor precision in information retrieval (IR) systems. Word sense disambiguation and discrimination methods have been defined to help systems choose which documents should be retrieved in relation to an ambiguous query. However, the only approaches that show a genuine benefit for word sense discrimination or disambiguation in IR are generally supervised ones. In this paper we propose a new unsupervised method that uses word sense discrimination in IR. The method we develop is based on spectral clustering and reorders an initially retrieved doc- ument list by boosting documents that are semantically similar to the target query. For several TREC ad hoc collections we show that our method is useful in the case of queries which contain ambiguous terms. We are interested in improving the level of precision after 5, 10 and 30 retrieved documents (P@5, P@10, P@30) respectively. We show that precision can be improved by 8% above current state-of-the-art baselines. We also focus on poor performing queries.
TRANSLATE with x
English
TRANSLATE with
Enable collaborative features and customize widget: Bing Webmaster Portal