# Transition-based Parsing with Lighter Feed-Forward Networks

arXiv: https://arxiv.org/abs/1810.08997 · HTML: https://mlsanity.com/paper/1810.08997/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Oct 2018.

## Built on by (most cited first, 2 of 2)

- [Bertinho: Galician BERT Representations](https://mlsanity.com/paper/2103.13799/) (2021)
- [Approximating CKY with Transformers](https://mlsanity.com/paper/2305.02386/) (2023)

## Abstract (arXiv)

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.