# Low-Resource Syntactic Transfer with Unsupervised Source Reordering

arXiv: https://arxiv.org/abs/1903.05683 · HTML: https://mlsanity.com/paper/1903.05683/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Mar 2019.

## Built on by (most cited first, 8 of 8)

- [PPT: Parsimonious Parser Transfer for Unsupervised Cross-Lingual Adaptation](https://mlsanity.com/paper/2101.11216/) (2021)
- ["Wikily" Supervised Neural Translation Tailored to Cross-Lingual Tasks](https://mlsanity.com/paper/2104.08384/) (2021)
- [Substructure Distribution Projection for Zero-Shot Cross-Lingual Dependency Parsing](https://mlsanity.com/paper/2110.08538/) (2021)
- [On the Relation between Syntactic Divergence and Zero-Shot Performance](https://mlsanity.com/paper/2110.04644/) (2021)
- [Improving Cross-Lingual Transfer through Subtree-Aware Word Reordering](https://mlsanity.com/paper/2310.13583/) (2023)
- [Word-order typology in Multilingual BERT: A case study in subordinate-clause detection](https://mlsanity.com/paper/2205.11987/) (2022)
- [Improving Low-Resource Cross-lingual Parsing with Expected Statistic Regularization](https://mlsanity.com/paper/2210.09428/) (2022)
- [Implicit Word Reordering with Knowledge Distillation for Cross-Lingual Dependency Parsing](https://mlsanity.com/paper/2502.17308/) (2025)

## Abstract (arXiv)

We describe a cross-lingual transfer method for dependency parsing that takes into account the problem of word order differences between source and target languages. Our model only relies on the Bible, a considerably smaller parallel data than the commonly used parallel data in transfer methods. We use the concatenation of projected trees from the Bible corpus, and the gold-standard treebanks in multiple source languages along with cross-lingual word representations. We demonstrate that reordering the source treebanks before training on them for a target language improves the accuracy of languages outside the European language family. Our experiments on 68 treebanks (38 languages) in the Universal Dependencies corpus achieve a high accuracy for all languages. Among them, our experiments on 16 treebanks of 12 non-European languages achieve an average UAS absolute improvement of 3.3% over a state-of-the-art method.