Abstract
Transformer-based language models achieve state-of-the-art results on several natural language processing tasks. One of these is textual entailment, i.e., the task of determining whether a premise logically entails a hypothesis. However, the models perform poorly on this task when the examples contain negations. In this paper, we propose a new definition of textual entailment that captures also negation. This allows us to develop TINA (Textual Inference with Negation Augmentation), a principled technique for negated data augmentation that can be combined with the unlikelihood loss function. Our experiments with different transformer-based models show that our method can significantly improve the performance of the models on textual entailment datasets with negation – without sacrificing performance on datasets without negation.- Anthology ID:
- 2022.findings-emnlp.301
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2022
- Month:
- December
- Year:
- 2022
- Address:
- Abu Dhabi, United Arab Emirates
- Editors:
- Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4086–4099
- Language:
- URL:
- https://aclanthology.org/2022.findings-emnlp.301
- DOI:
- 10.18653/v1/2022.findings-emnlp.301
- Cite (ACL):
- Chadi Helwe, Simon Coumes, Chloé Clavel, and Fabian Suchanek. 2022. TINA: Textual Inference with Negation Augmentation. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 4086–4099, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
- Cite (Informal):
- TINA: Textual Inference with Negation Augmentation (Helwe et al., Findings 2022)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-1/2022.findings-emnlp.301.pdf