Learning word sense distributions, detecting unattested senses and identifying novel senses using topic models
JH Lau, P Cook, D McCarthy, S Gella, T Baldwin
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) | Association for Computing Machinery (ACM) | Published : 2014
Unsupervised word sense disambiguation (WSD) methods are an attractive approach to all-words WSD due to their non-reliance on expensive annotated data. Unsupervised estimates of sense frequency have been shown to be very useful for WSD due to the skewed nature of word sense distributions. This paper presents a fully unsupervised topic modelling-based approach to sense frequency estimation, which is highly portable to different corpora and sense inventories, in being applicable to any part of speech, and not requiring a hierarchical sense inventory, parsing or parallel text. We demonstrate the effectiveness of the method over the tasks of predominant sense learning and sense distribution acqu..View full abstract
We wish to thank the anonymous reviewers for their valuable comments. This research was supported in part by funding from the Australian Research Council.