Few-shot Relation Extraction (FSRE) aims to extract relational facts from a sparse set of labeled corpora. Recent studies have shown promising results in FSRE by employing Pre-trained Language Models (PLMs) within the framework of supervised contrastive learning, which considers both instances and label facts. However, how to effectively harness massive instance-label pairs to encompass the learned representation with semantic richness in this learning paradigm is not fully explored. To address this gap, we introduce a novel synergistic anchored contrastive pre-training framework. This framework is motivated by the insight that the diverse viewpoints conveyed through instance-label pairs capture incomplete yet complementary intrinsic textual semantics. Specifically, our framework involves a symmetrical contrastive objective that encompasses both sentence-anchored and label-anchored contrastive losses. By combining these two losses, the model establishes a robust and uniform representation space. This space effectively captures the reciprocal alignment of feature distributions among instances and relational facts, simultaneously enhancing the maximization of mutual information across diverse perspectives within the same relation. Experimental results demonstrate that our framework achieves significant performance enhancements compared to baseline models in downstream FSRE tasks. Furthermore, our approach exhibits superior adaptability to handle the challenges of domain shift and zero-shot relation extraction. Our code is available online at https://github.com/AONE-NLP/FSRE-SaCon.

翻译：小样本关系抽取（FSRE）旨在从稀疏标注的语料中提取关系事实。近年来，在监督对比学习框架内采用预训练语言模型（PLMs）的研究在FSRE中取得了显著成果，该方法同时考虑了实例和标签事实。然而，如何有效利用海量实例-标签对，使所学表示蕴含语义丰富性这一学习范式尚未得到充分探索。为此，我们提出了一种新颖的协同锚点对比预训练框架。该框架源于以下洞察：通过实例-标签对传递的多元视角能够捕捉到不完整却互补的内在文本语义。具体而言，我们的框架包含一个对称对比目标，涵盖句子锚点和标签锚点两类对比损失。通过结合这两种损失，模型构建了一个鲁棒且统一的表示空间。该空间能够有效捕捉实例与关系事实之间特征分布的互逆对齐，同时增强同一关系内不同视角间的互信息最大化。实验结果表明，与基线模型相比，我们的框架在下游FSRE任务中实现了显著的性能提升。此外，我们的方法在应对领域迁移和零样本关系抽取挑战时展现出卓越的适应性。相关代码已开源至 https://github.com/AONE-NLP/FSRE-SaCon。