Cross-Lingual SRL Based upon Universal Dependencies

@inproceedings{Prazk2017CrossLingualSB,
  title={Cross-Lingual SRL Based upon Universal Dependencies},
  author={Ondrej Praz{\'a}k and Miloslav Konop{\'i}k},
  booktitle={RANLP},
  year={2017}
}
In this paper, we introduce a cross-lingual Semantic Role Labeling (SRL) system with language independent features based upon Universal Dependencies. We propose two methods to convert SRL annotations from monolingual dependency trees into universal dependency trees. Our SRL system is based upon cross-lingual features derived from universal dependency trees and supervised learning that utilizes a maximum entropy classifier. We design experiments to verify whether the Universal Dependencies are… CONTINUE READING