Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Effective Inference for Generative Neural Parsing

About

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.

Mitchell Stern, Daniel Fried, Dan Klein• 2017

Related benchmarks

TaskDatasetResultRank
Constituency ParsingWSJ Penn Treebank (test)
F1 Score92.56
27
Constituency ParsingPTB WSJ (Section 23 test)
F1 Score92.56
12
Showing 2 of 2 rows

Other info

Follow for update