Abstract
We recently introduced DRaiL, a declarative neural-symbolic modeling framework designed to support a wide variety of NLP scenarios. In this paper, we enhance DRaiL with an easy to use Python interface, equipped with methods to define, modify and augment DRaiL models interactively, as well as with methods to debug and visualize the predictions made. We demonstrate this interface with a challenging NLP task: predicting sentence and entity level moral sentiment in political tweets.- Anthology ID:
- 2022.emnlp-demos.37
- Volume:
- Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
- Month:
- December
- Year:
- 2022
- Address:
- Abu Dhabi, UAE
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 371–378
- Language:
- URL:
- https://aclanthology.org/2022.emnlp-demos.37
- DOI:
- 10.18653/v1/2022.emnlp-demos.37
- Cite (ACL):
- Maria Leonor Pacheco, Shamik Roy, and Dan Goldwasser. 2022. Hands-On Interactive Neuro-Symbolic NLP with DRaiL. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 371–378, Abu Dhabi, UAE. Association for Computational Linguistics.
- Cite (Informal):
- Hands-On Interactive Neuro-Symbolic NLP with DRaiL (Pacheco et al., EMNLP 2022)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/2022.emnlp-demos.37.pdf