# Parameter sharing between dependency parsers for related languages

arXiv: https://arxiv.org/abs/1808.09055 · HTML: https://mlsanity.com/paper/1808.09055/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Aug 2018.

## Built on by (most cited first, 5 of 5)

- [Does Typological Blinding Impede Cross-Lingual Sharing?](https://mlsanity.com/paper/2101.11888/) (2021)
- [Language Embeddings for Typology and Cross-lingual Transfer Learning](https://mlsanity.com/paper/2106.02082/) (2021)
- [Systematic Investigation of Strategies Tailored for Low-Resource Settings for Low-Resource Dependency Parsing](https://mlsanity.com/paper/2201.11374/) (2022)
- [MACT: Model-Agnostic Cross-Lingual Training for Discourse Representation Structure Parsing](https://mlsanity.com/paper/2406.01052/) (2024)
- [Typological Feature Prediction with Large Language Models: An In-Context Learning Approach](https://mlsanity.com/paper/2609.03775/) (2026)

## Abstract (arXiv)

Previous work has suggested that parameter sharing between transition-based neural dependency parsers for related languages can lead to better performance, but there is no consensus on what parameters to share. We present an evaluation of 27 different parameter sharing strategies across 10 languages, representing five pairs of related languages, each pair from a different language family. We find that sharing transition classifier parameters always helps, whereas the usefulness of sharing word and/or character LSTM parameters varies. Based on this result, we propose an architecture where the transition classifier is shared, and the sharing of word and character parameters is controlled by a parameter that can be tuned on validation data. This model is linguistically motivated and obtains significant improvements over a monolingually trained baseline. We also find that sharing transition classifier parameters helps when training a parser on unrelated language pairs, but we find that, in the case of unrelated languages, sharing too many parameters does not help.