@inproceedings{zhao-etal-2018-generalizing,
    title = "Generalizing Word Embeddings using Bag of Subwords",
    author = "Zhao, Jinman  and
      Mudgal, Sidharth  and
      Liang, Yingyu",
    booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing",
    month = oct # "-" # nov,
    year = "2018",
    address = "Brussels, Belgium",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/D18-1059",
    doi = "10.18653/v1/D18-1059",
    pages = "601--606",
    abstract = "We approach the problem of generalizing pre-trained word embeddings beyond fixed-size vocabularies without using additional contextual information. We propose a subword-level word vector generation model that views words as bags of character $n$-grams. The model is simple, fast to train and provides good vectors for rare or unseen words. Experiments show that our model achieves state-of-the-art performances in English word similarity task and in joint prediction of part-of-speech tag and morphosyntactic attributes in 23 languages, suggesting our model{'}s ability in capturing the relationship between words{'} textual representations and their embeddings.",
}