Sussx: WSD using automatically acquired predominant senses

Authors:
Rob Koeling;Diana McCarthy
Affiliations:
University of Sussex, Brighton, UK;University of Sussex, Brighton, UK
Venue:
SemEval '07 Proceedings of the 4th International Workshop on Semantic Evaluations
Year:
2007

Citing 4
Cited 4

The role of domain information in Word Sense Disambiguation

Natural Language Engineering
Automatic retrieval and clustering of similar words

COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 2
Finding predominant word senses in untagged text

ACL '04 Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics
Domain-specific sense distributions and predominant sense acquisition

HLT '05 Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing

Unsupervised large-vocabulary word sense disambiguation with graph-based algorithms for sequence data labeling

HLT '05 Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing
Knowledge-rich Word Sense Disambiguation rivaling supervised systems

ACL '10 Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics
Multilingual WSD with just a few lines of code: the BabelNet API

ACL '12 Proceedings of the ACL 2012 System Demonstrations
BabelNet: The automatic construction, evaluation and application of a wide-coverage multilingual semantic network

Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

We introduced a method for discovering the predominant sense of words automatically using raw (unlabelled) text in (McCarthy et al., 2004) and participated with this system in Senseval3. Since then, we worked on further developing ideas to improve upon the base method. In the current paper we target two areas where we believe there is potential for improvement. In the first one we address the finegrained structure of WordNet's (wn) sense inventory (i.e. the topic of the task in this particular track). The second issue we address here, deals with topic domain specilisation of the base method.