@inproceedings{vilares-gomez-rodriguez-2018-transition-based,
    title = "Transition-based Parsing with Lighter Feed-Forward Networks",
    author = "Vilares, David  and
      G{\'o}mez-Rodr{\'i}guez, Carlos",
    editor = "de Marneffe, Marie-Catherine  and
      Lynn, Teresa  and
      Schuster, Sebastian",
    booktitle = "Proceedings of the Second Workshop on Universal Dependencies ({UDW} 2018)",
    month = nov,
    year = "2018",
    address = "Brussels, Belgium",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/W18-6019/",
    doi = "10.18653/v1/W18-6019",
    pages = "162--172",
    abstract = "We explore whether it is possible to build lighter parsers, that are statistically equivalent to their corresponding standard version, for a wide set of languages showing different structures and morphologies. As testbed, we use the Universal Dependencies and transition-based dependency parsers trained on feed-forward networks. For these, most existing research assumes \textit{de facto standard} embedded features and relies on pre-computation tricks to obtain speed-ups. We explore how these features and their size can be reduced and whether this translates into speed-ups with a negligible impact on accuracy. The experiments show that \textit{grand-daughter} features can be removed for the majority of treebanks without a significant (negative or positive) LAS difference. They also show how the size of the embeddings can be notably reduced."
}