@inproceedings{shi-etal-2017-combining,
    title = "Combining Global Models for Parsing {U}niversal {D}ependencies",
    author = "Shi, Tianze  and
      Wu, Felix G.  and
      Chen, Xilun  and
      Cheng, Yao",
    editor = "Haji{\v{c}}, Jan  and
      Zeman, Dan",
    booktitle = "Proceedings of the {C}o{NLL} 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies",
    month = aug,
    year = "2017",
    address = "Vancouver, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/K17-3003/",
    doi = "10.18653/v1/K17-3003",
    pages = "31--39",
    abstract = "We describe our entry, C2L2, to the CoNLL 2017 shared task on parsing Universal Dependencies from raw text. Our system features an ensemble of three global parsing paradigms, one graph-based and two transition-based. Each model leverages character-level bi-directional LSTMs as lexical feature extractors to encode morphological information. Though relying on baseline tokenizers and focusing only on parsing, our system ranked second in the official end-to-end evaluation with a macro-average of 75.00 LAS F1 score over 81 test treebanks. In addition, we had the top average performance on the four surprise languages and on the small treebank subset."
}