Fast(er) Exact Decoding and Global Training for Transition-based Dependency Parsing via a Minimal Feature Set

Abstract
We first present a minimal feature set for transition-based dependency parsing, continuing a recent trend started by Kiperwasser and Goldberg (2016a) and Cross and Huang (2016a) of using bi-directional LSTM features. We plug our minimal feature set into the dynamic-programming framework of Huang and Sagae (2010) and Kuhlmann et al. (2011) to produce the first implementation of worst-case O(n^3) exact decoders for arc-hybrid and arc-eager transition systems. With our minimal features, we also present O(n^3) global training methods. Finally, using ensembles including our new parsers, we achieve the best unlabeled attachment score reported (to our knowledge) on the Chinese Treebank and the "second-best-in-class" result on the English Penn Treebank.

@InProceedings{shi-huang-lee:2017:EMNLP2017,
    author    = {Shi, Tianze  and  Huang, Liang  and  Lee, Lillian},
    title     = {Fast(er) Exact Decoding and Global Training for Transition-Based Dependency Parsing via a Minimal Feature Set},
    booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing},
    month     = {September},
    year      = {2017},
    address   = {Copenhagen, Denmark},
    publisher = {Association for Computational Linguistics},
    pages     = {12--23},
    url       = {https://www.aclweb.org/anthology/D17-1002}
}