# On the Relation between Syntactic Divergence and Zero-Shot Performance

arXiv: https://arxiv.org/abs/2110.04644 · HTML: https://mlsanity.com/paper/2110.04644/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 38 references that are in the map.
- First posted on arXiv 9 Oct 2021.

## Builds on (most cited first, 20 of 20)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [AllenNLP: A Deep Semantic Natural Language Processing Platform](https://mlsanity.com/paper/1803.07640/) (2018)
- [Deep Biaffine Attention for Neural Dependency Parsing](https://mlsanity.com/paper/1611.01734/) (2016)
- [Cross-Lingual Alignment of Contextual Word Embeddings, with Applications to Zero-shot Dependency Parsing](https://mlsanity.com/paper/1902.09492/) (2019)
- [Trankit: A Light-Weight Transformer-based Toolkit for Multilingual Natural Language Processing](https://mlsanity.com/paper/2101.03289/) (2021)
- [Cross-Lingual BERT Transformation for Zero-Shot Dependency Parsing](https://mlsanity.com/paper/1909.06775/) (2019)
- [Many Languages, One Parser](https://mlsanity.com/paper/1602.01595/) (2016)
- [Enhancing Machine Translation with Dependency-Aware Self-Attention](https://mlsanity.com/paper/1909.03149/) (2019)
- [Universal Semantic Parsing](https://mlsanity.com/paper/1702.03196/) (2017)
- [Improved Neural Machine Translation with a Syntax-Aware Encoder and Decoder](https://mlsanity.com/paper/1707.05436/) (2017)
- [Polyglot Contextual Representations Improve Crosslingual Transfer](https://mlsanity.com/paper/1902.09697/) (2019)
- [Target Language-Aware Constrained Inference for Cross-lingual Dependency Parsing](https://mlsanity.com/paper/1909.01482/) (2019)
- [Syntax-Directed Attention for Neural Machine Translation](https://mlsanity.com/paper/1711.04231/) (2017)
- [Multitask Parsing Across Semantic Representations](https://mlsanity.com/paper/1805.00287/) (2018)
- [Fine-Grained Analysis of Cross-Linguistic Syntactic Divergences](https://mlsanity.com/paper/2005.03436/) (2020)
- [Low-Resource Syntactic Transfer with Unsupervised Source Reordering](https://mlsanity.com/paper/1903.05683/) (2019)
- [Lexical Semantic Recognition](https://mlsanity.com/paper/2004.15008/) (2020)
- [pyBART: Evidence-based Syntactic Transformations for IE](https://mlsanity.com/paper/2005.01306/) (2020)
- [Zero-Shot Cross-Lingual Dependency Parsing through Contextual Embedding Transformation](https://mlsanity.com/paper/2103.02212/) (2021)
- [Part of Speech and Universal Dependency effects on English Arabic Machine Translation](https://mlsanity.com/paper/2106.00745/) (2021)

## Built on by (most cited first, 4 of 4)

- [MultiTACRED: A Multilingual Version of the TAC Relation Extraction Dataset](https://mlsanity.com/paper/2305.04582/) (2023)
- [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)
- [Assessing the Role of Lexical Semantics in Cross-lingual Transfer through Controlled Manipulations](https://mlsanity.com/paper/2408.07599/) (2024)

## Abstract (arXiv)

We explore the link between the extent to which syntactic relations are preserved in translation and the ease of correctly constructing a parse tree in a zero-shot setting. While previous work suggests such a relation, it tends to focus on the macro level and not on the level of individual edges-a gap we aim to address. As a test case, we take the transfer of Universal Dependencies (UD) parsing from English to a diverse set of languages and conduct two sets of experiments. In one, we analyze zero-shot performance based on the extent to which English source edges are preserved in translation. In another, we apply three linguistically motivated transformations to UD, creating more cross-lingually stable versions of it, and assess their zero-shot parsability. In order to compare parsing performance across different schemes, we perform extrinsic evaluation on the downstream task of cross-lingual relation extraction (RE) using a subset of a popular English RE benchmark translated to Russian and Korean. In both sets of experiments, our results suggest a strong relation between cross-lingual stability and zero-shot parsing performance.