arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2201.10927cs.CL
收藏

用于自然语言推理的对级有监督对比学习

Pair-Level Supervised Contrastive Learning for Natural Language Inference

Tsinghua University(清华大学)

Shu'ang Li, Xuming Hu, Li Lin, Lijie Wen

摘要:

自然语言推理(NLI)是自然语言理解中一项日益重要的任务,它要求人们推断句子对(前提和假设)之间的关系。最近的许多研究都使用了对比学习,通过结合NLI数据集的句子对的关系来学习句子表示。然而,这些方法仅关注与双级表示的比较。在本文中,我们提出了一个对级监督对比学习方法(PairSCL)。我们采用交叉注意模块来学习句子对的联合表征。对比学习的目的是通过将一类句子对拉在一起,将另一类句子对推开来区分不同类别的句子对。我们在NLI的两个公共数据集上对PairSCL进行了评估,其中PairSCL的准确性平均优于其他方法2.1%。此外,我们的方法优于以前的国家的最先进的方法上的七个转移任务的文本分类。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑