Quasi bidirectional encoder representations from transformers for Word Sense Disambiguation

While contextualized embeddings have produced performance breakthroughs in many Natural Language Processing (NLP) tasks, Word Sense Disambiguation (WSD) has not benefited from them yet. In this paper, we introduce QBERT, a Transformer based architecture for contextualized embeddings which makes use of a coattentive layer to produce more deeply bidirectional representations, better-fitting for the WSD task. As a result, we are able to train a WSD system that beats the state of the art on the concatenation of all evaluation datasets by over 3 points, also outperforming a comparable model using ELMo