@inproceedings{lu-etal-2016-multi-prototype,
    title = "Multi-prototype {C}hinese Character Embedding",
    author = "Lu, Yanan  and
      Zhang, Yue  and
      Ji, Donghong",
    editor = "Calzolari, Nicoletta  and
      Choukri, Khalid  and
      Declerck, Thierry  and
      Goggi, Sara  and
      Grobelnik, Marko  and
      Maegaard, Bente  and
      Mariani, Joseph  and
      Mazo, Helene  and
      Moreno, Asuncion  and
      Odijk, Jan  and
      Piperidis, Stelios",
    booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
    month = may,
    year = "2016",
    address = "Portoro{\v{z}}, Slovenia",
    publisher = "European Language Resources Association (ELRA)",
    url = "https://preview.aclanthology.org/fix-sig-urls/L16-1138/",
    pages = "855--859",
    abstract = "Chinese sentences are written as sequences of characters, which are elementary units of syntax and semantics. Characters are highly polysemous in forming words. We present a position-sensitive skip-gram model to learn multi-prototype Chinese character embeddings, and explore the usefulness of such character embeddings to Chinese NLP tasks. Evaluation on character similarity shows that multi-prototype embeddings are significantly better than a single-prototype baseline. In addition, used as features in the Chinese NER task, the embeddings result in a 1.74{\%} F-score improvement over a state-of-the-art baseline."
}