@inproceedings{schick-schutze-2019-attentive,
    title = "Attentive Mimicking: Better Word Embeddings by Attending to Informative Contexts",
    author = {Schick, Timo  and
      Sch{\"u}tze, Hinrich},
    editor = "Burstein, Jill  and
      Doran, Christy  and
      Solorio, Thamar",
    booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
    month = jun,
    year = "2019",
    address = "Minneapolis, Minnesota",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/N19-1048/",
    doi = "10.18653/v1/N19-1048",
    pages = "489--494",
    abstract = "Learning high-quality embeddings for rare words is a hard problem because of sparse context information. Mimicking (Pinter et al., 2017) has been proposed as a solution: given embeddings learned by a standard algorithm, a model is first trained to reproduce embeddings of frequent words from their surface form and then used to compute embeddings for rare words. In this paper, we introduce attentive mimicking: the mimicking model is given access not only to a word`s surface form, but also to all available contexts and learns to attend to the most informative and reliable contexts for computing an embedding. In an evaluation on four tasks, we show that attentive mimicking outperforms previous work for both rare and medium-frequency words. Thus, compared to previous work, attentive mimicking improves embeddings for a much larger part of the vocabulary, including the medium-frequency range."
}