What's Going On in Neural Constituency Parsers? An Analysis
This addresses the shift from rule-based to neural parsing for NLP researchers, showing neural methods can replicate classical insights, but it is incremental as it confirms trends rather than introducing new techniques.
The paper analyzes whether neural constituency parsers capture the same information as classical systems that used explicit grammars and lexicons, finding that a high-performance neural model (92.08 F1 on PTB) implicitly learns much of this information, suggesting neural machinery can subsume traditional scaffolding.
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.