How to identify semantic relations among entities in a document when only a few labeled documents are available? Few-shot document-level relation extraction (FSDLRE) is crucial for addressing the pervasive data scarcity problem in real-world scenarios. Metric-based meta-learning is an effective framework widely adopted for FSDLRE, which constructs class prototypes for classification. However, existing works often struggle to obtain class prototypes with accurate relational semantics: 1) To build prototype for a target relation type, they aggregate the representations of all entity pairs holding that relation, while these entity pairs may also hold other relations, thus disturbing the prototype. 2) They use a set of generic NOTA (none-of-the-above) prototypes across all tasks, neglecting that the NOTA semantics differs in tasks with different target relation types. In this paper, we propose a relation-aware prototype learning method for FSDLRE to strengthen the relational semantics of prototype representations. By judiciously leveraging the relation descriptions and realistic NOTA instances as guidance, our method effectively refines the relation prototypes and generates task-specific NOTA prototypes. Extensive experiments demonstrate that our method outperforms state-of-the-art approaches by average 2.61% $F_1$ across various settings of two FSDLRE benchmarks.

翻译：如何仅利用少量标注文档识别文档中实体间的语义关系？少样本文档级关系抽取（FSDLRE）对于解决现实场景中普遍存在的数据稀缺问题至关重要。基于度量的元学习是广泛用于FSDLRE的有效框架，通过构建类别原型进行分类。然而，现有工作往往难以获得具有准确关系语义的类别原型：1）为目标关系类型构建原型时，它们聚合所有具有该关系的实体对的表征，但这些实体对可能同时包含其他关系，从而干扰原型。2）它们在所有任务中使用一组通用的NOTA（无关类别）原型，忽略了不同目标关系类型的任务中NOTA语义存在差异。本文提出一种面向FSDLRE的关系感知原型学习方法，以增强原型表征的关系语义。通过巧妙利用关系描述和真实NOTA实例作为引导，本方法有效精炼关系原型并生成任务特定的NOTA原型。大量实验表明，在两个FSDLRE基准的多种设置下，本方法平均$F_1$值较现有最优方法提升2.61%。