Cross-Lingual Syntactic Transfer with Limited Resources

TL;DR

This paper presents a straightforward approach for cross-lingual dependency parsing that effectively leverages limited translation data, improving performance across multiple languages by combining word clustering, lexical transfer, and annotation projection techniques.

Contribution

It introduces a novel three-step method for cross-lingual syntactic transfer that works well with small translation datasets, outperforming previous state-of-the-art methods.

Findings

Significant improvements over previous methods with Bible translation data

Additional gains using Europarl corpus as translation data

Effective across 38 Universal Dependencies datasets

Abstract

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.