Inducing Interpretability in Knowledge Graph Embeddings

. Chandrahas, Tathagata Sengupta, Cibi Pragadeesh, Partha Talukdar


Abstract
We study the problem of inducing interpretability in Knowledge Graph (KG) embeddings. Learning KG embeddings has been an active area of research in the past few years, resulting in many different models. However, most of these methods do not address the interpretability (semantics) of individual dimensions of the learned embeddings. In this work, we study this problem and propose a method for inducing interpretability in KG embeddings using entity co-occurrence statistics. The proposed method significantly improves the interpretability, while maintaining comparable performance in other KG tasks.
Anthology ID:
2020.icon-main.9
Volume:
Proceedings of the 17th International Conference on Natural Language Processing (ICON)
Month:
December
Year:
2020
Address:
Indian Institute of Technology Patna, Patna, India
Editors:
Pushpak Bhattacharyya, Dipti Misra Sharma, Rajeev Sangal
Venue:
ICON
SIG:
Publisher:
NLP Association of India (NLPAI)
Note:
Pages:
70–75
Language:
URL:
https://aclanthology.org/2020.icon-main.9
DOI:
Bibkey:
Cite (ACL):
. Chandrahas, Tathagata Sengupta, Cibi Pragadeesh, and Partha Talukdar. 2020. Inducing Interpretability in Knowledge Graph Embeddings. In Proceedings of the 17th International Conference on Natural Language Processing (ICON), pages 70–75, Indian Institute of Technology Patna, Patna, India. NLP Association of India (NLPAI).
Cite (Informal):
Inducing Interpretability in Knowledge Graph Embeddings (Chandrahas et al., ICON 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.icon-main.9.pdf