A Cluster-based Approach for Improving Isotropy in Contextual Embedding Space

Sara Rajaee, Mohammad Taher Pilehvar


Abstract
The representation degeneration problem in Contextual Word Representations (CWRs) hurts the expressiveness of the embedding space by forming an anisotropic cone where even unrelated words have excessively positive correlations. Existing techniques for tackling this issue require a learning process to re-train models with additional objectives and mostly employ a global assessment to study isotropy. Our quantitative analysis over isotropy shows that a local assessment could be more accurate due to the clustered structure of CWRs. Based on this observation, we propose a local cluster-based method to address the degeneration issue in contextual embedding spaces. We show that in clusters including punctuations and stop words, local dominant directions encode structural information, removing which can improve CWRs performance on semantic tasks. Moreover, we find that tense information in verb representations dominates sense semantics. We show that removing dominant directions of verb representations can transform the space to better suit semantic applications. Our experiments demonstrate that the proposed cluster-based method can mitigate the degeneration problem on multiple tasks.
Anthology ID:
2021.acl-short.73
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
575–584
Language:
URL:
https://aclanthology.org/2021.acl-short.73
DOI:
10.18653/v1/2021.acl-short.73
Bibkey:
Cite (ACL):
Sara Rajaee and Mohammad Taher Pilehvar. 2021. A Cluster-based Approach for Improving Isotropy in Contextual Embedding Space. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 575–584, Online. Association for Computational Linguistics.
Cite (Informal):
A Cluster-based Approach for Improving Isotropy in Contextual Embedding Space (Rajaee & Pilehvar, ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-short.73.pdf
Video:
 https://aclanthology.org/2021.acl-short.73.mp4
Code
 Sara-Rajaee/clusterbased_isotropy_enhancement
Data
BoolQCoLAGLUEMRPCSICKSSTSST-2WiC