Abstract
Cross-lingual Transfer Learning typically involves training a model on a high-resource sourcelanguage and applying it to a low-resource tar-get language. In this work we introduce a lexi-cal database calledValency Patterns Leipzig(ValPal)which provides the argument patterninformation about various verb-forms in mul-tiple languages including low-resource langua-ges. We also provide a framework to integratethe ValPal database knowledge into the state-of-the-art LSTM based model for cross-lingualsemantic role labelling. Experimental resultsshow that integrating such knowledge resultedin am improvement in performance of the mo-del on all the target languages on which it isevaluated.- Anthology ID:
- 2022.deelio-1.1
- Volume:
- Proceedings of Deep Learning Inside Out (DeeLIO 2022): The 3rd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures
- Month:
- May
- Year:
- 2022
- Address:
- Dublin, Ireland and Online
- Venue:
- DeeLIO
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1–10
- Language:
- URL:
- https://aclanthology.org/2022.deelio-1.1
- DOI:
- 10.18653/v1/2022.deelio-1.1
- Cite (ACL):
- Chinmay Choudhary and Colm O’Riordan. 2022. Cross-lingual Semantic Role Labelling with the ValPaL Database Knowledge. In Proceedings of Deep Learning Inside Out (DeeLIO 2022): The 3rd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures, pages 1–10, Dublin, Ireland and Online. Association for Computational Linguistics.
- Cite (Informal):
- Cross-lingual Semantic Role Labelling with the ValPaL Database Knowledge (Choudhary & O’Riordan, DeeLIO 2022)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/2022.deelio-1.1.pdf