Self-supervised sentence representation learning is the task of constructing an embedding
space for sentences without relying on human annotation efforts. One straightforward …

In this paper, we introduce the task of learning unsupervised dialogue embeddings. Trivial
approaches such as combining pre-trained word or sentence embeddings and encoding …

This paper presents miCSE, a mutual information-based contrastive learning framework that
significantly advances the state-of-the-art in few-shot sentence embedding. The proposed …

Unsupervised sentence embeddings learning has been recently dominated by contrastive
learning methods (eg, SimCSE), which keep positive pairs similar and push negative pairs …

Document representation is the basis of language modeling. Its goal is to turn natural
language text that flows into a structured form that can be stored and processed by a …

Pre-trained transformer models shine in many natural language processing tasks and
therefore are expected to bear the representation of the input sentence or text meaning …

This paper improves contrastive learning for sentence embeddings from two perspectives:
handling dropout noise and addressing feature corruption. Specifically, for the first …

Ensembling a neural network is a widely recognized approach to enhance model
performance, estimate uncertainty, and improve robustness in deep supervised learning …

Abstract Pre-trained Language Model (PLM) is nowadays the mainstay of Unsupervised
Sentence Representation Learning (USRL). However, PLMs are sensitive to the frequency …

Self-supervised sentence representation learning is the task of constructing an embedding
space for sentences without relying on human annotation efforts. One straightforward …