Supporting Clustering with Contrastive Learning

Dejiao Zhang, Feng Nan, Xiaokai Wei, Shang-Wen Li, Henghui Zhu, Kathleen McKeown, Ramesh Nallapati, Andrew O. Arnold, Bing Xiang


Abstract
Unsupervised clustering aims at discovering the semantic categories of data according to some distance measured in the representation space. However, different categories often overlap with each other in the representation space at the beginning of the learning process, which poses a significant challenge for distance-based clustering in achieving good separation between different categories. To this end, we propose Supporting Clustering with Contrastive Learning (SCCL) – a novel framework to leverage contrastive learning to promote better separation. We assess the performance of SCCL on short text clustering and show that SCCL significantly advances the state-of-the-art results on most benchmark datasets with 3%-11% improvement on Accuracy and 4%-15% improvement on Normalized Mutual Information. Furthermore, our quantitative analysis demonstrates the effectiveness of SCCL in leveraging the strengths of both bottom-up instance discrimination and top-down clustering to achieve better intra-cluster and inter-cluster distances when evaluated with the ground truth cluster labels.
Anthology ID:
2021.naacl-main.427
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
June
Year:
2021
Address:
Online
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5419–5430
Language:
URL:
https://aclanthology.org/2021.naacl-main.427
DOI:
10.18653/v1/2021.naacl-main.427
Bibkey:
Cite (ACL):
Dejiao Zhang, Feng Nan, Xiaokai Wei, Shang-Wen Li, Henghui Zhu, Kathleen McKeown, Ramesh Nallapati, Andrew O. Arnold, and Bing Xiang. 2021. Supporting Clustering with Contrastive Learning. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5419–5430, Online. Association for Computational Linguistics.
Cite (Informal):
Supporting Clustering with Contrastive Learning (Zhang et al., NAACL 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2021.naacl-main.427.pdf
Video:
 https://preview.aclanthology.org/ingestion-script-update/2021.naacl-main.427.mp4
Code
 amazon-research/sccl +  additional community code
Data
AG News