Abstract
Taxonomies are valuable resources for many applications, but the limited coverage due to the expensive manual curation process hinders their general applicability. Prior works attempt to automatically expand existing taxonomies to improve their coverage by learning concept embeddings in Euclidean space, while taxonomies, inherently hierarchical, more naturally align with the geometric properties of a hyperbolic space. In this paper, we present HyperExpan, a taxonomy expansion algorithm that seeks to preserve the structure of a taxonomy in a more expressive hyperbolic embedding space and learn to represent concepts and their relations with a Hyperbolic Graph Neural Network (HGNN). Specifically, HyperExpan leverages position embeddings to exploit the structure of the existing taxonomies, and characterizes the concept profile information to support the inference on new concepts that are unseen during training. Experiments show that our proposed HyperExpan outperforms baseline models with representation learning in a Euclidean feature space and achieves state-of-the-art performance on the taxonomy expansion benchmarks.- Anthology ID:
- 2021.findings-emnlp.353
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2021
- Month:
- November
- Year:
- 2021
- Address:
- Punta Cana, Dominican Republic
- Editors:
- Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
- Venue:
- Findings
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4182–4194
- Language:
- URL:
- https://aclanthology.org/2021.findings-emnlp.353
- DOI:
- 10.18653/v1/2021.findings-emnlp.353
- Cite (ACL):
- Mingyu Derek Ma, Muhao Chen, Te-Lin Wu, and Nanyun Peng. 2021. HyperExpan: Taxonomy Expansion with Hyperbolic Representation Learning. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 4182–4194, Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- HyperExpan: Taxonomy Expansion with Hyperbolic Representation Learning (Ma et al., Findings 2021)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-3/2021.findings-emnlp.353.pdf
- Data
- Microsoft Academic Graph