期刊论文

Wu, C

英文

Machine Learning

0885-6125

2023

112

12

4837-4861

10.1007/s10994-023-06408-8

This work was supported by the Major Program of National Fund of Philosophy and Social Science of China (Grant No. 19ZDA345), National Natural Science Foundation of China (Grant No. 71804055), the Hebei Provincial Natural Science Foundation (Grant No. 2022CFB006), the China Postdoctoral Science Foundation 590 (Grant No. 2021M701368), and Fundamental Research Funds for the Central Universities (Grant No. CCNU21XJ039), Fundamental Research Funds for the Central Universities (Grant No. CCNU22QN016).

本校为第一且通讯机构

Unsupervised sentence embedding learning is a fundamental task in natural language processing. Recently, unsupervised contrastive learning based on pre-trained language models has shown impressive performance in sentence embedding learning. This method aims to align positive sentence pairs while pushing apart negative sentence pairs to achieve semantic uniformity in the representation space. However, most previous literature leverages a random strategy to sample negative pairs, which suffers from the risk of selecting uninformative negative examples (e.g., easily distinguishable examples, anis...