# Fine-Grained Analysis of Cross-Linguistic Syntactic Divergences

arXiv: https://arxiv.org/abs/2005.03436 · HTML: https://mlsanity.com/paper/2005.03436/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 May 2020.

## Built on by (most cited first, 9 of 9)

- [Meta-learning via Language Model In-context Tuning](https://mlsanity.com/paper/2110.07814/) (2021)
- [To Diverge or Not to Diverge: A Morphosyntactic Perspective on Machine Translation vs Human Translation](https://mlsanity.com/paper/2401.01419/) (2024)
- [PreQuEL: Quality Estimation of Machine Translation Outputs in Advance](https://mlsanity.com/paper/2205.09178/) (2022)
- [Semantics-aware Attention Improves Neural Machine Translation](https://mlsanity.com/paper/2110.06920/) (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)
- [Part of Speech and Universal Dependency effects on English Arabic Machine Translation](https://mlsanity.com/paper/2106.00745/) (2021)
- [Locally Measuring Cross-lingual Lexical Alignment: A Domain and Word Level Perspective](https://mlsanity.com/paper/2410.07239/) (2024)
- [Unsupervised Cross-Lingual Part-of-Speech Tagging with Monolingual Corpora Only](https://mlsanity.com/paper/2602.09366/) (2026)

## Abstract (arXiv)

The patterns in which the syntax of different languages converges and diverges are often used to inform work on cross-lingual transfer. Nevertheless, little empirical work has been done on quantifying the prevalence of different syntactic divergences across language pairs. We propose a framework for extracting divergence patterns for any language pair from a parallel corpus, building on Universal Dependencies. We show that our framework provides a detailed picture of cross-language divergences, generalizes previous approaches, and lends itself to full automation. We further present a novel dataset, a manually word-aligned subset of the Parallel UD corpus in five languages, and use it to perform a detailed corpus study. We demonstrate the usefulness of the resulting analysis by showing that it can help account for performance patterns of a cross-lingual parser.