An Efficient Self-Supervised Cross-View Training For Sentence Embedding
This work addresses the problem of efficient sentence embedding for NLP practitioners by narrowing the performance gap between large and small models, though it is incremental as it builds on existing contrastive learning approaches.
The paper tackles the performance degradation of self-supervised sentence embedding methods with smaller pretrained language models (PLMs) by proposing Self-supervised Cross-View Training (SCT), which outperforms competitors in 18 out of 21 cases for PLMs with less than 100M parameters across seven STS benchmarks.
Self-supervised sentence representation learning is the task of constructing an embedding space for sentences without relying on human annotation efforts. One straightforward approach is to finetune a pretrained language model (PLM) with a representation learning method such as contrastive learning. While this approach achieves impressive performance on larger PLMs, the performance rapidly degrades as the number of parameters decreases. In this paper, we propose a framework called Self-supervised Cross-View Training (SCT) to narrow the performance gap between large and small PLMs. To evaluate the effectiveness of SCT, we compare it to 5 baseline and state-of-the-art competitors on seven Semantic Textual Similarity (STS) benchmarks using 5 PLMs with the number of parameters ranging from 4M to 340M. The experimental results show that STC outperforms the competitors for PLMs with less than 100M parameters in 18 of 21 cases.