English

Polyglot Semantic Role Labeling

Computation and Language 2018-05-30 v1

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.

Keywords

Cite

@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}
}

Comments

To appear at ACL 2018

R2 v1 2026-06-23T02:12:20.450Z