Abstract
Adjectives like pretty, beautiful and gorgeous describe positive properties of the nouns they modify but with different intensity. These differences are important for natural language understanding and reasoning. We propose a novel BERT-based approach to intensity detection for scalar adjectives. We model intensity by vectors directly derived from contextualised representations and show they can successfully rank scalar adjectives. We evaluate our models both intrinsically, on gold standard datasets, and on an Indirect Question Answering task. Our results demonstrate that BERT encodes rich knowledge about the semantics of scalar adjectives, and is able to provide better quality intensity rankings than static embeddings and previous models with access to dedicated resources.- Anthology ID:
- 2020.emnlp-main.598
- Volume:
- Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Editors:
- Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 7371–7385
- Language:
- URL:
- https://aclanthology.org/2020.emnlp-main.598
- DOI:
- 10.18653/v1/2020.emnlp-main.598
- Cite (ACL):
- Aina Garí Soler and Marianna Apidianaki. 2020. BERT Knows Punta Cana is not just beautiful, it’s gorgeous: Ranking Scalar Adjectives with Contextualised Representations. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 7371–7385, Online. Association for Computational Linguistics.
- Cite (Informal):
- BERT Knows Punta Cana is not just beautiful, it’s gorgeous: Ranking Scalar Adjectives with Contextualised Representations (Garí Soler & Apidianaki, EMNLP 2020)
- PDF:
- https://preview.aclanthology.org/corrections-2024-05/2020.emnlp-main.598.pdf
- Code
- ainagari/scalar_adjs
- Data
- Flickr30k