@inproceedings{boyd-graber-etal-2020-evaluations,
    title = "Which Evaluations Uncover Sense Representations that Actually Make Sense?",
    author = "Boyd-Graber, Jordan  and
      Guo, Fenfei  and
      Findlater, Leah  and
      Iyyer, Mohit",
    editor = "Calzolari, Nicoletta  and
      B{\'e}chet, Fr{\'e}d{\'e}ric  and
      Blache, Philippe  and
      Choukri, Khalid  and
      Cieri, Christopher  and
      Declerck, Thierry  and
      Goggi, Sara  and
      Isahara, Hitoshi  and
      Maegaard, Bente  and
      Mariani, Joseph  and
      Mazo, H{\'e}l{\`e}ne  and
      Moreno, Asuncion  and
      Odijk, Jan  and
      Piperidis, Stelios",
    booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
    month = may,
    year = "2020",
    address = "Marseille, France",
    publisher = "European Language Resources Association",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2020.lrec-1.214/",
    pages = "1727--1738",
    language = "eng",
    ISBN = "979-10-95546-34-4",
    abstract = "Text representations are critical for modern natural language processing. One form of text representation, sense-specific embeddings, reflect a word`s sense in a sentence better than single-prototype word embeddings tied to each type. However, existing sense representations are not uniformly better: although they work well for computer-centric evaluations, they fail for human-centric tasks like inspecting a language`s sense inventory. To expose this discrepancy, we propose a new coherence evaluation for sense embeddings. We also describe a minimal model (Gumbel Attention for Sense Induction) optimized for discovering interpretable sense representations that are more coherent than existing sense embeddings."
}