Cross-Lingual SRL Based upon Universal Dependencies
Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017 (2017)
Research topics:
Semantic AnalysisAbstract
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 a supervised learning that utilizes a maximum entropy classifier. We design experiments to verify whether the Universal Dependencies are suitable for the cross-lingual SRL. The results are very promising and they open new interesting research paths for the future.
Authors
BibTex
@InProceedings{pravzak-konopik:2017:RANLP, author = {Pra\v{z}\'{a}k, Ond\v{r}ej and Konopik, Miloslav}, title = {Cross-Lingual SRL Based upon Universal Dependencies}, booktitle = {Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017}, month = {September}, year = {2017}, address = {Varna, Bulgaria}, publisher = {INCOMA Ltd.}, pages = {592--600}, abstract = {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 a supervised learning that utilizes a maximum entropy classifier. We design experiments to verify whether the Universal Dependencies are suitable for the cross-lingual SRL. The results are very promising and they open new interesting research paths for the future.}, url = {https://doi.org/10.26615/978-954-452-049-6_077} }
