Don't Neglect the Obvious: On the Role of Unambiguous Words in Word Sense Disambiguation
Abstract
State-of-the-art methods for Word Sense Disambiguation (WSD) combine two different features: the power of pre-trained language models and a propagation method to extend the coverage of such models. This propagation is needed as current sense-annotated corpora lack coverage of many instances in the underlying sense inventory (usually WordNet). At the same time, unambiguous words make for a large portion of all words in WordNet, while being poorly covered in existing sense-annotated corpora. In this paper, we propose a simple method to provide annotations for most unambiguous words in a large corpus. We introduce the UWA (Unambiguous Word Annotations) dataset and show how a state-of-the-art propagation-based model can use it to extend the coverage and quality of its word sense embeddings by a significant margin, improving on its original results on WSD.
- Publication:
-
arXiv e-prints
- Pub Date:
- April 2020
- DOI:
- 10.48550/arXiv.2004.14325
- arXiv:
- arXiv:2004.14325
- Bibcode:
- 2020arXiv200414325L
- Keywords:
-
- Computer Science - Computation and Language
- E-Print:
- Accepted to EMNLP 2020. Website: http://danlou.github.io/uwa