English

Transferring Semantic Roles Using Translation and Syntactic Information

Computation and Language 2017-10-05 v1

Abstract

Our paper addresses the problem of annotation projection for semantic role labeling for resource-poor languages using supervised annotations from a resource-rich language through parallel data. We propose a transfer method that employs information from source and target syntactic dependencies as well as word alignment density to improve the quality of an iterative bootstrapping method. Our experiments yield a 3.53.5 absolute labeled F-score improvement over a standard annotation projection method.

Keywords

Cite

@article{arxiv.1710.01411,
  title  = {Transferring Semantic Roles Using Translation and Syntactic Information},
  author = {Maryam Aminian and Mohammad Sadegh Rasooli and Mona Diab},
  journal= {arXiv preprint arXiv:1710.01411},
  year   = {2017}
}
R2 v1 2026-06-22T22:03:02.877Z