Distilling an Ensemble of Greedy Dependency Parsers into One MST Parser

Adhiguna Kuncoro1, Miguel Ballesteros2, Lingpeng Kong1, Chris Dyer3, Noah A. Smith4
1Carnegie Mellon University, 2Pompeu Fabra University, 3Google DeepMind, 4University of Washington


Abstract

We introduce two first-order graph-based dependency parsers achieving a new state of the art. The first is a consensus parser built from an ensemble of independently trained greedy LSTM transition-based parsers with different random initializations. We cast this approach as minimum Bayes risk decoding (under the Hamming cost) and argue that weaker consensus within the ensemble is a useful signal of difficulty or ambiguity. The second parser is a “distillation” of the ensemble into a single model. We train the distillation parser using a structured hinge loss objective with a novel cost that incorporates ensemble uncertainty estimates for each possible attachment, thereby avoiding the intractable cross-entropy computations required by applying standard distillation objectives to problems with structured outputs. The first-order distillation parser matches or surpasses the state of the art on English, Chinese, and German.