Knowledge Representation Learning with Contrastive Completion Coding

Bo Ouyang, Wenbing Huang, Runfa Chen, Zhixing Tan, Yang Liu, Maosong Sun, Jihong Zhu


Abstract
Knowledge representation learning (KRL) has been used in plenty of knowledge-driven tasks. Despite fruitfully progress, existing methods still suffer from the immaturity on tackling potentially-imperfect knowledge graphs and highly-imbalanced positive-negative instances during training, both of which would hinder the performance of KRL. In this paper, we propose Contrastive Completion Coding (C3), a novel KRL framework that is composed of two functional components: 1. Hierarchical Architecture, which integrates both low-level standalone features and high-level topology-aware features to yield robust embedding for each entity/relation. 2. Normalized Contrasitive Training, which conducts normalized one-to-many contrasitive learning to emphasize different negatives with different weights, delivering better convergence compared to conventional training losses. Extensive experiments on several benchmarks verify the efficacy of the two proposed techniques and combing them together generally achieves superior performance against state-of-the-art approaches.
Anthology ID:
2021.findings-emnlp.263
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:
3061–3073
Language:
URL:
https://aclanthology.org/2021.findings-emnlp.263
DOI:
10.18653/v1/2021.findings-emnlp.263
Bibkey:
Cite (ACL):
Bo Ouyang, Wenbing Huang, Runfa Chen, Zhixing Tan, Yang Liu, Maosong Sun, and Jihong Zhu. 2021. Knowledge Representation Learning with Contrastive Completion Coding. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 3061–3073, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Knowledge Representation Learning with Contrastive Completion Coding (Ouyang et al., Findings 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-2024-clasp/2021.findings-emnlp.263.pdf
Video:
 https://preview.aclanthology.org/ingest-2024-clasp/2021.findings-emnlp.263.mp4
Data
FB15k-237