Chinese Metaphorical Relation Extraction: Dataset and Models
Guihua Chen, Tiantian Wu, MiaoMiao Cheng, Xu Han, Jiefu Gong, Shijin Wang, Wei Song
Abstract
Metaphor identification is usually formulated as a sequence labeling or a syntactically related word-pair classification problem. In this paper, we propose a novel formulation of metaphor identification as a relation extraction problem. We introduce metaphorical relations, which are links between two spans, a target span and a source-related span, which are realized in sentences. Based on spans, we can use more flexible and precise text units beyond single words for capturing the properties of the target and the source. We create a dataset for Chinese metaphorical relation extraction, with more than 4,200 sentences annotated with metaphorical relations, corresponding target/source-related spans, and fine-grained span types. We develop a span-based end-to-end model for metaphorical relation extraction and demonstrate its effectiveness. We expect that metaphorical relation extraction can serve as a bridge for connecting linguistic and conceptual metaphor processing. The dataset is at https://github.com/cnunlp/CMRE.- Anthology ID:
- 2023.findings-emnlp.609
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2023
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 9085–9095
- Language:
- URL:
- https://preview.aclanthology.org/build-pipeline-with-new-library/2023.findings-emnlp.609/
- DOI:
- 10.18653/v1/2023.findings-emnlp.609
- Cite (ACL):
- Guihua Chen, Tiantian Wu, MiaoMiao Cheng, Xu Han, Jiefu Gong, Shijin Wang, and Wei Song. 2023. Chinese Metaphorical Relation Extraction: Dataset and Models. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 9085–9095, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Chinese Metaphorical Relation Extraction: Dataset and Models (Chen et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/build-pipeline-with-new-library/2023.findings-emnlp.609.pdf