# Cross-Lingual Syntactic Transfer with Limited Resources

arXiv: https://arxiv.org/abs/1610.06227 · HTML: https://mlsanity.com/paper/1610.06227/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Oct 2016.

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

- [PAXQA: Generating Cross-lingual Question Answering Examples at Training Scale](https://mlsanity.com/paper/2304.12206/) (2023)
- [Compositional Generalization in Multilingual Semantic Parsing over Wikidata](https://mlsanity.com/paper/2108.03509/) (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)
- [Morphological Processing of Low-Resource Languages: Where We Are and What's Next](https://mlsanity.com/paper/2203.08909/) (2022)
- [Improving Cross-Lingual Transfer through Subtree-Aware Word Reordering](https://mlsanity.com/paper/2310.13583/) (2023)
- [Word Alignment in the Era of Deep Learning: A Tutorial](https://mlsanity.com/paper/2212.00138/) (2022)
- [Improving Low-Resource Cross-lingual Parsing with Expected Statistic Regularization](https://mlsanity.com/paper/2210.09428/) (2022)

## Abstract (arXiv)

We describe a simple but effective method for cross-lingual syntactic transfer of dependency parsers, in the scenario where a large amount of translation data is not available. The method makes use of three steps: 1) a method for deriving cross-lingual word clusters, which can then be used in a multilingual parser; 2) a method for transferring lexical information from a target language to source language treebanks; 3) a method for integrating these steps with the density-driven annotation projection method of Rasooli and Collins (2015). Experiments show improvements over the state-of-the-art in several languages used in previous work, in a setting where the only source of translation data is the Bible, a considerably smaller corpus than the Europarl corpus used in previous work. Results using the Europarl corpus as a source of translation data show additional improvements over the results of Rasooli and Collins (2015). We conclude with results on 38 datasets from the Universal Dependencies corpora.