Paper: Cross-lingual Transfer of Semantic Role Labeling Models

ACL ID P13-1117
Title Cross-lingual Transfer of Semantic Role Labeling Models
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2013
Authors

Semantic Role Labeling (SRL) has be- come one of the standard tasks of natural language processing and proven useful as a source of information for a number of other applications. We address the prob- lem of transferring an SRL model from one language to another using a shared feature representation. This approach is then evaluated on three language pairs, demonstrating competitive performance as compared to a state-of-the-art unsuper- vised SRL system and a cross-lingual an- notation projection baseline. We also con- sider the contribution of different aspects of the feature representation to the perfor- mance of the model and discuss practical applicability of this method.