TNCSE: Tensor's Norm Constraints for Unsupervised Contrastive Learning of Sentence Embeddings

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zong, Tianyu, Shi, Bingkang, Yi, Hongzhu, Xu, Jungang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913739124506624
author Zong, Tianyu
Shi, Bingkang
Yi, Hongzhu
Xu, Jungang
author_facet Zong, Tianyu
Shi, Bingkang
Yi, Hongzhu
Xu, Jungang
contents Unsupervised sentence embedding representation has become a hot research topic in natural language processing. As a tensor, sentence embedding has two critical properties: direction and norm. Existing works have been limited to constraining only the orientation of the samples' representations while ignoring the features of their module lengths. To address this issue, we propose a new training objective that optimizes the training of unsupervised contrastive learning by constraining the module length features between positive samples. We combine the training objective of Tensor's Norm Constraints with ensemble learning to propose a new Sentence Embedding representation framework, TNCSE. We evaluate seven semantic text similarity tasks, and the results show that TNCSE and derived models are the current state-of-the-art approach; in addition, we conduct extensive zero-shot evaluations, and the results show that TNCSE outperforms other baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2503_12739
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TNCSE: Tensor's Norm Constraints for Unsupervised Contrastive Learning of Sentence Embeddings
Zong, Tianyu
Shi, Bingkang
Yi, Hongzhu
Xu, Jungang
Computation and Language
Artificial Intelligence
Unsupervised sentence embedding representation has become a hot research topic in natural language processing. As a tensor, sentence embedding has two critical properties: direction and norm. Existing works have been limited to constraining only the orientation of the samples' representations while ignoring the features of their module lengths. To address this issue, we propose a new training objective that optimizes the training of unsupervised contrastive learning by constraining the module length features between positive samples. We combine the training objective of Tensor's Norm Constraints with ensemble learning to propose a new Sentence Embedding representation framework, TNCSE. We evaluate seven semantic text similarity tasks, and the results show that TNCSE and derived models are the current state-of-the-art approach; in addition, we conduct extensive zero-shot evaluations, and the results show that TNCSE outperforms other baselines.
title TNCSE: Tensor's Norm Constraints for Unsupervised Contrastive Learning of Sentence Embeddings
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2503.12739