Effective Inference for Generative Neural Parsing
This work addresses a bottleneck in generative parsing for NLP researchers, enabling direct decoding and improving accuracy, though it is incremental as it builds on existing models.
The paper tackled the problem of decoding in generative neural parsing models, which previously required external parsers, by developing an improved inference procedure that achieved 92.56 F1 on the Penn Treebank, surpassing prior state-of-the-art results for single-model systems.
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.