Transition-based Parsing with Lighter Feed-Forward Networks

David Vilares, Carlos Gómez-Rodríguez


Abstract
We explore whether it is possible to build lighter parsers, that are statistically equivalent to their corresponding standard version, for a wide set of languages showing different structures and morphologies. As testbed, we use the Universal Dependencies and transition-based dependency parsers trained on feed-forward networks. For these, most existing research assumes de facto standard embedded features and relies on pre-computation tricks to obtain speed-ups. We explore how these features and their size can be reduced and whether this translates into speed-ups with a negligible impact on accuracy. The experiments show that grand-daughter features can be removed for the majority of treebanks without a significant (negative or positive) LAS difference. They also show how the size of the embeddings can be notably reduced.
Anthology ID:
W18-6019
Volume:
Proceedings of the Second Workshop on Universal Dependencies (UDW 2018)
Month:
November
Year:
2018
Address:
Brussels, Belgium
Venue:
UDW
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
162–172
Language:
URL:
https://aclanthology.org/W18-6019
DOI:
10.18653/v1/W18-6019
Bibkey:
Cite (ACL):
David Vilares and Carlos Gómez-Rodríguez. 2018. Transition-based Parsing with Lighter Feed-Forward Networks. In Proceedings of the Second Workshop on Universal Dependencies (UDW 2018), pages 162–172, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Transition-based Parsing with Lighter Feed-Forward Networks (Vilares & Gómez-Rodríguez, UDW 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/starsem-semeval-split/W18-6019.pdf