@inproceedings{yuan-strohmaier-2021-cambridge,
    title = "{C}ambridge at {S}em{E}val-2021 Task 2: Neural {W}i{C}-Model with Data Augmentation and Exploration of Representation",
    author = "Yuan, Zheng  and
      Strohmaier, David",
    editor = "Palmer, Alexis  and
      Schneider, Nathan  and
      Schluter, Natalie  and
      Emerson, Guy  and
      Herbelot, Aurelie  and
      Zhu, Xiaodan",
    booktitle = "Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)",
    month = aug,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2021.semeval-1.96/",
    doi = "10.18653/v1/2021.semeval-1.96",
    pages = "730--737",
    abstract = "This paper describes the system of the Cambridge team submitted to the SemEval-2021 shared task on Multilingual and Cross-lingual Word-in-Context Disambiguation. Building on top of a pre-trained masked language model, our system is first pre-trained on out-of-domain data, and then fine-tuned on in-domain data. We demonstrate the effectiveness of the proposed two-step training strategy and the benefits of data augmentation from both existing examples and new resources. We further investigate different representations and show that the addition of distance-based features is helpful in the word-in-context disambiguation task. Our system yields highly competitive results in the cross-lingual track without training on any cross-lingual data; and achieves state-of-the-art results in the multilingual track, ranking first in two languages (Arabic and Russian) and second in French out of 171 submitted systems."
}