Abstract
Metaphors are ubiquitous in natural language, and detecting them requires contextual reasoning about whether a semantic incongruence actually exists. Most existing work addresses this problem using pre-trained contextualized models. Despite their success, these models require a large amount of labeled data and are not linguistically-based. In this paper, we proposed a ContrAstive pre-Trained modEl (CATE) for metaphor detection with semi-supervised learning. Our model first uses a pre-trained model to obtain a contextual representation of target words and employs a contrastive objective to promote an increased distance between target words’ literal and metaphorical senses based on linguistic theories. Furthermore, we propose a simple strategy to collect large-scale candidate instances from the general corpus and generalize the model via self-training. Extensive experiments show that CATE achieves better performance against state-of-the-art baselines on several benchmark datasets.- Anthology ID:
- 2021.emnlp-main.316
- Volume:
- Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
- Month:
- November
- Year:
- 2021
- Address:
- Online and Punta Cana, Dominican Republic
- Editors:
- Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3888–3898
- Language:
- URL:
- https://aclanthology.org/2021.emnlp-main.316
- DOI:
- 10.18653/v1/2021.emnlp-main.316
- Cite (ACL):
- Zhenxi Lin, Qianli Ma, Jiangyue Yan, and Jieyu Chen. 2021. CATE: A Contrastive Pre-trained Model for Metaphor Detection with Semi-supervised Learning. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 3888–3898, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- CATE: A Contrastive Pre-trained Model for Metaphor Detection with Semi-supervised Learning (Lin et al., EMNLP 2021)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-3/2021.emnlp-main.316.pdf