Latent Tree Learning with Differentiable Parsers: Shift-Reduce Parsing and Chart Parsing

Jean Maillard, Stephen Clark


Abstract
Latent tree learning models represent sentences by composing their words according to an induced parse tree, all based on a downstream task. These models often outperform baselines which use (externally provided) syntax trees to drive the composition order. This work contributes (a) a new latent tree learning model based on shift-reduce parsing, with competitive downstream performance and non-trivial induced trees, and (b) an analysis of the trees learned by our shift-reduce model and by a chart-based model.
Anthology ID:
W18-2903
Volume:
Proceedings of the Workshop on the Relevance of Linguistic Structure in Neural Architectures for NLP
Month:
July
Year:
2018
Address:
Melbourne, Australia
Venues:
ACL | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
13–18
Language:
URL:
https://www.aclweb.org/anthology/W18-2903
DOI:
10.18653/v1/W18-2903
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/W18-2903.pdf