Language Modelling Makes Sense: Propagating Representations through WordNet for Full-Coverage Word Sense Disambiguation
This work addresses the challenge of full-coverage word sense disambiguation for natural language processing applications, representing a strong specific gain rather than a broad paradigm shift.
The authors tackled the problem of meaning conflation in word embeddings by using contextual embeddings from neural language modeling to achieve unprecedented gains in Word Sense Disambiguation (WSD), with a simple k-NN method consistently surpassing previous systems.
Contextual embeddings represent a new generation of semantic representations learned from Neural Language Modelling (NLM) that addresses the issue of meaning conflation hampering traditional word embeddings. In this work, we show that contextual embeddings can be used to achieve unprecedented gains in Word Sense Disambiguation (WSD) tasks. Our approach focuses on creating sense-level embeddings with full-coverage of WordNet, and without recourse to explicit knowledge of sense distributions or task-specific modelling. As a result, a simple Nearest Neighbors (k-NN) method using our representations is able to consistently surpass the performance of previous systems using powerful neural sequencing models. We also analyse the robustness of our approach when ignoring part-of-speech and lemma features, requiring disambiguation against the full sense inventory, and revealing shortcomings to be improved. Finally, we explore applications of our sense embeddings for concept-level analyses of contextual embeddings and their respective NLMs.