Abstract
We describe a transfer method based on annotation projection to develop a dependency-based semantic role labeling system for languages for which no supervised linguistic information other than parallel data is available. Unlike previous work that presumes the availability of supervised features such as lemmas, part-of-speech tags, and dependency parse trees, we only make use of word and character features. Our deep model considers using character-based representations as well as unsupervised stem embeddings to alleviate the need for supervised features. Our experiments outperform a state-of-the-art method that uses supervised lexico-syntactic features on 6 out of 7 languages in the Universal Proposition Bank.- Anthology ID:
- W19-0417
- Volume:
- Proceedings of the 13th International Conference on Computational Semantics - Long Papers
- Month:
- May
- Year:
- 2019
- Address:
- Gothenburg, Sweden
- Editors:
- Simon Dobnik, Stergios Chatzikyriakidis, Vera Demberg
- Venue:
- IWCS
- SIG:
- SIGSEM
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 200–210
- Language:
- URL:
- https://aclanthology.org/W19-0417
- DOI:
- 10.18653/v1/W19-0417
- Cite (ACL):
- Maryam Aminian, Mohammad Sadegh Rasooli, and Mona Diab. 2019. Cross-Lingual Transfer of Semantic Roles: From Raw Text to Semantic Roles. In Proceedings of the 13th International Conference on Computational Semantics - Long Papers, pages 200–210, Gothenburg, Sweden. Association for Computational Linguistics.
- Cite (Informal):
- Cross-Lingual Transfer of Semantic Roles: From Raw Text to Semantic Roles (Aminian et al., IWCS 2019)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/W19-0417.pdf