Polyglot Semantic Role Labeling

TL;DR

This paper introduces a polyglot approach to semantic role labeling that leverages cross-lingual similarities, improving performance across multiple languages without relying on parallel data.

Contribution

It presents a novel multilingual SRL method that combines resources from different languages, outperforming monolingual models even with dissimilar annotations and no parallel data.

Findings

Improved SRL performance across multiple languages.

Polyglot model benefits low-resource languages.

No parallel data needed for cross-lingual transfer.

Abstract

Previous approaches to multilingual semantic dependency parsing treat languages independently, without exploiting the similarities between semantic structures across languages. We experiment with a new approach where we combine resources from a pair of languages in the CoNLL 2009 shared task to build a polyglot semantic role labeler. Notwithstanding the absence of parallel data, and the dissimilarity in annotations between languages, our approach results in an improvement in SRL performance on multiple languages over a monolingual baseline. Analysis of the polyglot model shows it to be advantageous in lower-resource settings.