%0 Conference Proceedings %T Fast(er) Exact Decoding and Global Training for Transition-Based Dependency Parsing via a Minimal Feature Set %A Shi, Tianze %A Huang, Liang %A Lee, Lillian %Y Palmer, Martha %Y Hwa, Rebecca %Y Riedel, Sebastian %S Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing %D 2017 %8 September %I Association for Computational Linguistics %C Copenhagen, Denmark %F shi-etal-2017-fast %X 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(n³) exact decoders for arc-hybrid and arc-eager transition systems. With our minimal features, we also present O(n³) 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. %R 10.18653/v1/D17-1002 %U https://aclanthology.org/D17-1002 %U https://doi.org/10.18653/v1/D17-1002 %P 12-23