Fine-Grained Analysis of Cross-Linguistic Syntactic Divergences
This work addresses the need for empirical quantification of syntactic divergences to inform cross-lingual transfer in natural language processing, though it is incremental as it builds on existing approaches.
The authors tackled the problem of quantifying syntactic divergences across language pairs by proposing a framework for extracting divergence patterns from parallel corpora using Universal Dependencies, and they demonstrated its utility by showing it helps account for performance patterns in a cross-lingual parser.
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.