Cross-lingual Transfer of Semantic Role Labeling Models
Mikhail Kozhevnikov and Ivan Titov
The 51st Annual Meeting of the Association for Computational Linguistics (ACL 2013)
Sofia, Bulgaria, August 4-9, 2013
Semantic Role Labeling (SRL) has become 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 problem 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 unsupervised SRL system and a cross-lingual annotation projection baseline. We also consider the contribution of different aspects of the feature representation to the performance of the model and discuss practical applicability of this method.
Conference Manager (V2.61.0 - Rev. 2792M)