Natural language inference (NLI) is an increasingly important task for
natural language understanding, which requires one to infer the relationship
between the sentence pair (premise and hypothesis). Many recent works have used
contrastive learning by incorporating the relationship of the sentence pair
from NLI datasets to learn sentence representation. However, these methods only
focus on comparisons with sentence-level representations. In this paper, we
propose a Pair-level Supervised Contrastive Learning approach (PairSCL). We
adopt a cross attention module to learn the joint representations of the
sentence pairs. A contrastive learning objective is designed to distinguish the
varied classes of sentence pairs by pulling those in one class together and
pushing apart the pairs in other classes. We evaluate PairSCL on two public
datasets of NLI where the accuracy of PairSCL outperforms other methods by 2.1%
on average. Furthermore, our method outperforms the previous state-of-the-art
method on seven transfer tasks of text classification.

本文提出一种基于对偶句子级别的监督对比学习（PairSCL）方法，采用交叉注意力机制学习句子对的联合表示，并使用对比学习目标来区分不同类别的句子对，在两个公共 NLI 数据集上，PairSCL 的准确性平均优于其他方法 2.1％，并在文本分类的七个转移任务上超过了先前的最新方法。

自然语言推理的对偶级别监督对比学习

Pair-Level Supervised Contrastive Learning for Natural Language Inference

Recently, there is rising interest in modelling the interactions of two
sentences with deep neural networks. However, most of the existing methods
encode two sequences with separate encoders, in which a sentence is encoded
with little or no information from the other sentence. In this paper, we
propose a deep architecture to model the strong interaction of sentence pair
with two coupled-LSTMs. Specifically, we introduce two coupled ways to model
the interdependences of two LSTMs, coupling the local contextualized
interactions of two sentences. We then aggregate these interactions and use a
dynamic pooling to select the most informative features. Experiments on two
very large datasets demonstrate the efficacy of our proposed architecture and
its superiority to state-of-the-art methods.

该研究提出了一种深度架构方法，使用耦合的 LSTM 来进行句子对的强交互建模，并采用动态池化来选择最具信息量的特征，实验证明其在两个大型数据集上具有优越性，优于现有的最先进方法。