@inproceedings{ek-bernardy-2020-composing,
    title = "Composing Byte-Pair Encodings for Morphological Sequence Classification",
    author = "Ek, Adam  and
      Bernardy, Jean-Philippe",
    editor = "de Marneffe, Marie-Catherine  and
      de Lhoneux, Miryam  and
      Nivre, Joakim  and
      Schuster, Sebastian",
    booktitle = "Proceedings of the Fourth Workshop on Universal Dependencies (UDW 2020)",
    month = dec,
    year = "2020",
    address = "Barcelona, Spain (Online)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2020.udw-1.9/",
    pages = "76--86",
    abstract = "Byte-pair encodings is a method for splitting a word into sub-word tokens, a language model then assigns contextual representations separately to each of these tokens. In this paper, we evaluate four different methods of composing such sub-word representations into word representations. We evaluate the methods on morphological sequence classification, the task of predicting grammatical features of a word. Our experiments reveal that using an RNN to compute word representations is consistently more effective than the other methods tested across a sample of eight languages with different typology and varying numbers of byte-pair tokens per word."
}