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. |
Year | DOI | Venue |
---|---|---|
2018 | 10.18653/v1/p18-2075 | PROCEEDINGS OF THE 56TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 2 |
DocType | Volume | Citations |
Journal | abs/1806.03290 | 2 |
PageRank | References | Authors |
0.37 | 1 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Daniel Fried | 1 | 83 | 7.69 |
Dan Klein | 2 | 8083 | 495.21 |