Word Sense Disambiguation with Semi-Supervised Learning

Abstract

Current word sense disambiguation (WSD) systems based on supervised learning are still limited in that they do not work well for all words in a language. One of the main reasons is the lack of sufficient training data. In this paper, we investigate the use of unlabeled training data for WSD, in the framework of semi-supervised learning. Four semi-supervised learning algorithms are evaluated on 29 nouns of Senseval-2 (SE2) English lexical sample task and SE2 En-glish all-words task. Empirical results show that unlabeled data can bring significant improvement in WSD accuracy.

Cite

Text

Pham et al. "Word Sense Disambiguation with Semi-Supervised Learning." AAAI Conference on Artificial Intelligence, 2005.

Markdown

[Pham et al. "Word Sense Disambiguation with Semi-Supervised Learning." AAAI Conference on Artificial Intelligence, 2005.](https://mlanthology.org/aaai/2005/pham2005aaai-word/)

BibTeX

@inproceedings{pham2005aaai-word,
  title     = {{Word Sense Disambiguation with Semi-Supervised Learning}},
  author    = {Pham, Thanh Phong and Ng, Hwee Tou and Lee, Wee Sun},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2005},
  pages     = {1093-1098},
  url       = {https://mlanthology.org/aaai/2005/pham2005aaai-word/}
}