What’s Going On in Neural Constituency Parsers? An Analysis

David Gaddy, Mitchell Stern, Dan Klein


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.
Anthology ID:
N18-1091
Volume:
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)
Month:
June
Year:
2018
Address:
New Orleans, Louisiana
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
999–1010
Language:
URL:
https://aclanthology.org/N18-1091
DOI:
10.18653/v1/N18-1091
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/N18-1091.pdf
Note:
 N18-1091.Notes.pdf
Code
 dgaddy/parser-analysis
Data
Penn Treebank