What's Going On in Neural Constituency Parsers? An Analysis
arXiv:1804.07853
Abstract
A number of differences have emerged between modern and classic approaches to constituency parsing in recent years, with structural components like grammars and feature-rich lexicons becoming less central while recurrent neural network representations rise in popularity. The goal of this work is to analyze the extent to which information provided directly by the model structure in classical systems is still being captured by neural methods. To this end, we propose a high-performance neural model (92.08 F1 on PTB) that is representative of recent work and perform a series of investigative experiments. We find that our model implicitly learns to encode much of the same information that was explicitly provided by grammars and lexicons in the past, indicating that this scaffolding can largely be subsumed by powerful general-purpose neural machinery.
arXiv commentNAACL 2018
References in corpus (6)
- Character-Aware Neural Language Models
- DyNet: The Dynamic Neural Network Toolkit
- Character-based Neural Machine Translation
- N-gram Language Modeling using Recurrent Neural Network Estimation
- Read, Tag, and Parse All at Once, or Fully-neural Dependency Parsing
- Investigating how well contextual features are captured by bi-directional recurrent neural network models