What Do Recurrent Neural Network Grammars Learn About Syntax?

Adhiguna Kuncoro, Miguel Ballesteros, Lingpeng Kong, Chris Dyer, Graham Neubig, Noah A. Smith


Abstract
Recurrent neural network grammars (RNNG) are a recently proposed probablistic generative modeling family for natural language. They show state-of-the-art language modeling and parsing performance. We investigate what information they learn, from a linguistic perspective, through various ablations to the model and the data, and by augmenting the model with an attention mechanism (GA-RNNG) to enable closer inspection. We find that explicit modeling of composition is crucial for achieving the best performance. Through the attention mechanism, we find that headedness plays a central role in phrasal representation (with the model’s latent attention largely agreeing with predictions made by hand-crafted head rules, albeit with some important differences). By training grammars without nonterminal labels, we find that phrasal representations depend minimally on nonterminals, providing support for the endocentricity hypothesis.
Anthology ID:
E17-1117
Volume:
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers
Month:
April
Year:
2017
Address:
Valencia, Spain
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1249–1258
Language:
URL:
https://www.aclweb.org/anthology/E17-1117
DOI:
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/E17-1117.pdf