近日,实验室博士生潘丁豪关于文档级关系抽取的研究被期刊 IEEE Transactions on Audio, Speech, and Language Processing (TASLP) 录用。TASLP 是自然语言处理领域顶级的国际期刊之一,影响因子4.1,是中国计算机学会推荐B类期刊,清华推荐A类期刊。
PLEM:基于原型学习的小样本文档级关系抽取方法
题目:PLEM: Prototype Learning with Evidence Match for Improving Few-Shot Document-Level Relation Extraction
摘要:Few-shot document-level relation extraction (FSDLRE) aims to develop a model with the ability to generalize to new categories in the context of document-level relation extraction, using a small number of support samples. Among others, metric based meta-learning methods are widely used in FSDLRE, which involve constructing class prototypes using the contextual representation of the entire document and the representation of entity pairs for relation classification. However, in relation classification, only a subset of sentences in a document, known as evidence, is required to determine the relationship category of entity pairs. In this paper, we propose a prototype learning method with evidence match (PLEM). By introducing an evidence matching auxiliary task in the process of relation prototype construction, the model is guided to focus more on the semantics of evidence sentences when building prototypes, thereby enhancing the relation prototypes. We further design task-specific evidence prototypes, enabling the model to adapt to the evidence semantic space of different relation categories. Extensive experimental results demonstrate that PLEM outperforms the state-of-the-art methods, achieving an average improvement of 1.23% in Macro F1 across various settings of two FSDLRE benchmarks.
中文摘要:小样本文档级关系抽取(Few-shot Document-Level Relation Extraction, FSDLRE)旨在构建能够在仅有少量支持样本的情况下推广到新关系类别的模型。在该任务中,基于度量的元学习方法被广泛应用,其核心思想是利用整篇文档的上下文表示和实体对的表示来构建关系类别的原型用于分类。然而,在实际的关系分类中,文档中只有部分句子(即“证据信息”)对于判断实体对之间的关系是必要且关键的。为此,本文提出了一种结合证据匹配机制的原型学习方法(PLEM)。通过在关系原型构建过程中引入证据匹配辅助任务,引导模型更关注这些关键证据句的语义,从而提升关系原型的质量。我们进一步设计了任务特定的证据原型,使模型能够适应不同关系类别下的证据语义空间。大量实验结果表明,PLEM在两个主流FSDLRE基准数据集上均优于现有最先进方法,在多个设定下提升了模型的性能。