Effective Inference for Generative Neural Parsing

Abstract

Generative neural models have recently achieved state-of-the-art results for constituency parsing. However, without a feasible search procedure, their use has so far been limited to reranking the output of external parsers in which decoding is more tractable. We describe an alternative to the conventional action-level beam search used for discriminative neural models that enables us to decode directly in these generative models. We then show that by improving our basic candidate selection strategy and using a coarse pruning function, we can improve accuracy while exploring significantly less of the search space. Applied to the model of Choe and Charniak (2016), our inference procedure obtains 92.56 F1 on section 23 of the Penn Treebank, surpassing prior state-of-the-art results for single-model systems.

EMNLP 2017

Cited by in corpus (6)

• Constituency Parsing with a Self-Attentive Encoder
• Automatic Business Process Structure Discovery using Ordered Neurons LSTM: A Preliminary Study
• Structural Supervision Improves Learning of Non-Local Grammatical Dependencies
• Representation of Constituents in Neural Language Models: Coordination Phrase as a Case Study
• Straight to the Tree: Constituency Parsing with Neural Syntactic Distance
• Dynamic Oracles for Top-Down and In-Order Shift-Reduce Constituent Parsing