Introduction to the special issue on word sense disambiguation: the state of the art
Computational Linguistics - Special issue on word sense disambiguation
Using corpus statistics and WordNet relations for sense identification
Computational Linguistics - Special issue on word sense disambiguation
TnT: a statistical part-of-speech tagger
ANLC '00 Proceedings of the sixth conference on Applied natural language processing
Unsupervised word sense disambiguation rivaling supervised methods
ACL '95 Proceedings of the 33rd annual meeting on Association for Computational Linguistics
ACL '94 Proceedings of the 32nd annual meeting on Association for Computational Linguistics
Integrating multiple knowledge sources to disambiguate word sense: an exemplar-based approach
ACL '96 Proceedings of the 34th annual meeting on Association for Computational Linguistics
Recognizing text genres with simple metrics using discriminant analysis
COLING '94 Proceedings of the 15th conference on Computational linguistics - Volume 2
HLT '93 Proceedings of the workshop on Human Language Technology
HLT '93 Proceedings of the workshop on Human Language Technology
An empirical study of the domain dependence of supervised word sense disambiguation systems
EMNLP '00 Proceedings of the 2000 Joint SIGDAT conference on Empirical methods in natural language processing and very large corpora: held in conjunction with the 38th Annual Meeting of the Association for Computational Linguistics - Volume 13
Exploring automatic word sense disambiguation with decision lists and the web
Proceedings of the COLING-2000 Workshop on Semantic Annotation and Intelligent Content
Feature Selection Analysis for Maximum Entropy-Based WSD
CICLing '02 Proceedings of the Third International Conference on Computational Linguistics and Intelligent Text Processing
Syntactic features and word similarity for supervised metonymy resolution
ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
Metonymy resolution as a classification task
EMNLP '02 Proceedings of the ACL-02 conference on Empirical methods in natural language processing - Volume 10
MEANING: a roadmap to knowledge technologies
COLING-Roadmap '02 Proceedings of the 2002 COLING workshop: A roadmap for computational linguistics - Volume 13
The bootstrapping of the Yarowsky algorithm in real corpora
Information Processing and Management: an International Journal
On robustness and domain adaptation using SVD for word sense disambiguation
COLING '08 Proceedings of the 22nd International Conference on Computational Linguistics - Volume 1
Supervised domain adaption for WSD
EACL '09 Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics
Word sense disambiguation using OntoNotes: an empirical study
EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing
SemEval-2010 task 17: all-words word sense disambiguation on a specific domain
DEW '09 Proceedings of the Workshop on Semantic Evaluations: Recent Achievements and Future Directions
Proceedings of the third international workshop on Data and text mining in bioinformatics
Coping with Distribution Change in the Same Domain Using Similarity-Based Instance Weighting
ACML '09 Proceedings of the 1st Asian Conference on Machine Learning: Advances in Machine Learning
International Journal of Data Mining and Bioinformatics
The SENSEVAL-2 panel on domains, topics and senses
SENSEVAL '01 The Proceedings of the Second International Workshop on Evaluating Word Sense Disambiguation Systems
Hi-index | 0.00 |
This paper revisits the one sense per collocation hypothesis using fine-grained sense distinctions and two different corpora. We show that the hypothesis is weaker for fine-grained sense distinctions (70% vs. 99% reported earlier on 2-way ambiguities). We also show that one sense per collocation does hold across corpora, but that collocations vary from one corpus to the other, following genre and topic variations. This explains the low results when performing word sense disambiguation across corpora. In fact, we demonstrate that when two independent corpora share a related genre/topic, the word sense disambiguation results would be better. Future work on word sense disambiguation will have to take into account genre and topic as important parameters on their models.