English

Transition-based Parsing with Lighter Feed-Forward Networks

Computation and Language 2018-10-23 v1

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.

Keywords

Cite

@article{arxiv.1810.08997,
  title  = {Transition-based Parsing with Lighter Feed-Forward Networks},
  author = {David Vilares and Carlos Gómez-Rodríguez},
  journal= {arXiv preprint arXiv:1810.08997},
  year   = {2018}
}

Comments

UD Workshop (co-located with EMNLP 2018)

R2 v1 2026-06-23T04:47:29.863Z