@InProceedings{fried-klein:2018:Short,
  author    = {Fried, Daniel  and  Klein, Dan},
  title     = {Policy Gradient as a Proxy for Dynamic Oracles in Constituency Parsing},
  booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)},
  month     = {July},
  year      = {2018},
  address   = {Melbourne, Australia},
  publisher = {Association for Computational Linguistics},
  pages     = {469--476},
  abstract  = {Dynamic oracles provide strong supervision for training constituency parsers with exploration, but must be custom defined for a given parser's transition system. We explore using a policy gradient method as a parser-agnostic alternative. In addition to directly optimizing for a tree-level metric such as F1, policy gradient has the potential to reduce exposure bias by allowing exploration during training; moreover, it does not require a dynamic oracle for supervision. On four constituency parsers in three languages, the method substantially outperforms static oracle likelihood training in almost all settings. For parsers where a dynamic oracle is available (including a novel oracle which we define for the transition system of Dyer et al., 2016), policy gradient typically recaptures a substantial fraction of the performance gain afforded by the dynamic oracle.},
  url       = {http://www.aclweb.org/anthology/P18-2075}
}