Unsupervised word sense disambiguation rivaling supervised methods. Yarowsky, D. In Proceedings of the 33rd annual meeting on Association for Computational Linguistics, of ACL '95, pages 189–196, USA, June, 1995. Association for Computational Linguistics.
Unsupervised word sense disambiguation rivaling supervised methods [link]Paper  doi  abstract   bibtex   
This paper presents an unsupervised learning algorithm for sense disambiguation that, when trained on unannotated English text, rivals the performance of supervised techniques that require time-consuming hand annotations. The algorithm is based on two powerful constraints—that words tend to have one sense per discourse and one sense per collocation—exploited in an iterative bootstrapping procedure. Tested accuracy exceeds 96%.
@inproceedings{yarowsky_unsupervised_1995,
	address = {USA},
	series = {{ACL} '95},
	title = {Unsupervised word sense disambiguation rivaling supervised methods},
	url = {https://doi.org/10.3115/981658.981684},
	doi = {10.3115/981658.981684},
	abstract = {This paper presents an unsupervised learning algorithm for sense disambiguation that, when trained on unannotated English text, rivals the performance of supervised techniques that require time-consuming hand annotations. The algorithm is based on two powerful constraints---that words tend to have one sense per discourse and one sense per collocation---exploited in an iterative bootstrapping procedure. Tested accuracy exceeds 96\%.},
	urldate = {2022-03-20},
	booktitle = {Proceedings of the 33rd annual meeting on {Association} for {Computational} {Linguistics}},
	publisher = {Association for Computational Linguistics},
	author = {Yarowsky, David},
	month = jun,
	year = {1995},
	pages = {189--196},
}

Downloads: 0