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.
@article{arxiv.1805.11598,
title = {Polyglot Semantic Role Labeling},
author = {Phoebe Mulcaire and Swabha Swayamdipta and Noah Smith},
journal= {arXiv preprint arXiv:1805.11598},
year = {2018}
}