Distributions of the senses of words are often highly skewed. This fact is exploited by word sense disambiguation (WSD) systems which back off to the predominant (most frequent) sense of a word when contextual clues are not strong enough. The topic domain of a document has a strong influence on the sense distribution of words. Unfortunately, it is not feasible to produce large manually sense-annotated corpora for every domain of interest. Previous experiments have shown that unsupervised estimation of the predominant sense of certain words using corpora whose domain has been determined by hand outperforms estimates based on domain-independent text for a subset of words and even outperforms the estimates based on counting occurrences in an annotated corpus.
In this paper we address the question of whether we can automatically produce domain-specific corpora which could be used to acquire predominant senses appropriate for specific domains. We collect the corpora by automatically classifying documents from a very large corpus of newswire text. Using these corpora we estimate the predominant sense of words for each domain. We first compare with the results presented in [1]. Encouraged by the results we start exploring using text categorization for WSD by evaluating on a standard data set (documents from the SENSEVAL-2 and 3 English all-word tasks). We show that for these documents and using domain-specific predominant senses, we are able to improve on the results that we obtained with predominant senses estimated using general, non domain-specific text. We also show that the confidence of the text classifier is a good indication whether it is worthwhile using the domain-specific predominant sense or not.
[1]
Diana McCarthy,et al.
Domain-Speci(cid:12)c Sense Distributions and Predominant Sense Acquisition
,
2022
.
[2]
Ted Pedersen,et al.
The cpan wordnet::similarity package
,
2003
.
[3]
Carlo Strapparava,et al.
The role of domain information in Word Sense Disambiguation
,
2002,
Natural Language Engineering.
[4]
George A. Miller,et al.
A Semantic Concordance
,
1993,
HLT.
[5]
Geoffrey Leech,et al.
100 Million Words of English:The British National Corpus (BNC)
,
1992
.
[6]
G. Leech.
100 million words of English
,
1993,
English Today.
[7]
Ted Briscoe,et al.
Robust Accurate Statistical Annotation of General Text
,
2002,
LREC.
[8]
Martha Palmer,et al.
The English all-words task
,
2004,
SENSEVAL@ACL.
[9]
Ted Pedersen,et al.
WordNet::Similarity - Measuring the Relatedness of Concepts
,
2004,
NAACL.
[10]
Dekang Lin,et al.
Automatic Retrieval and Clustering of Similar Words
,
1998,
ACL.
[11]
David W. Conrath,et al.
Semantic Similarity Based on Corpus Statistics and Lexical Taxonomy
,
1997,
ROCLING/IJCLCLP.
[12]
David Yarowsky,et al.
Evaluating sense disambiguation across diverse parameter spaces
,
2002,
Natural Language Engineering.
[13]
Julie Weeds,et al.
Finding Predominant Word Senses in Untagged Text
,
2004,
ACL.