@inproceedings{bevilacqua-navigli-2019-quasi,
    title = "Quasi Bidirectional Encoder Representations from Transformers for Word Sense Disambiguation",
    author = "Bevilacqua, Michele  and
      Navigli, Roberto",
    editor = "Mitkov, Ruslan  and
      Angelova, Galia",
    booktitle = "Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)",
    month = sep,
    year = "2019",
    address = "Varna, Bulgaria",
    publisher = "INCOMA Ltd.",
    url = "https://preview.aclanthology.org/iwcs-25-ingestion/R19-1015/",
    doi = "10.26615/978-954-452-056-4_015",
    pages = "122--131",
    abstract = "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 co-attentive 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."
}