Learning Numeracy: A Simple Yet Effective Number Embedding Approach Using Knowledge Graph

Hanyu Duan, Yi Yang, Kar Yan Tam


Abstract
Numeracy plays a key role in natural language understanding. However, existing NLP approaches, not only traditional word2vec approach or contextualized transformer-based language models, fail to learn numeracy. As the result, the performance of these models is limited when they are applied to number-intensive applications in clinical and financial domains. In this work, we propose a simple number embedding approach based on knowledge graph. We construct a knowledge graph consisting of number entities and magnitude relations. Knowledge graph embedding method is then applied to obtain number vectors. Our approach is easy to implement, and experiment results on various numeracy-related NLP tasks demonstrate the effectiveness and efficiency of our method.
Anthology ID:
2021.findings-emnlp.221
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:
2597–2602
Language:
URL:
https://aclanthology.org/2021.findings-emnlp.221
DOI:
10.18653/v1/2021.findings-emnlp.221
Bibkey:
Cite (ACL):
Hanyu Duan, Yi Yang, and Kar Yan Tam. 2021. Learning Numeracy: A Simple Yet Effective Number Embedding Approach Using Knowledge Graph. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 2597–2602, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Learning Numeracy: A Simple Yet Effective Number Embedding Approach Using Knowledge Graph (Duan et al., Findings 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.findings-emnlp.221.pdf
Video:
 https://aclanthology.org/2021.findings-emnlp.221.mp4
Code
 hduanac/nekg