轻量级模型实现零样本关系抽取，单次前向传播完成预测。
GLiREL -- Generalist Model for Zero-Shot Relation Extraction
- 基于实体对的上下文编码，单次前向传播预测关系
- 在FewRel和WikiZSL上达到当前最优性能
- 可生成多样关系标签的合成数据集构建协议
我们提出GLiREL（通用轻量级零样本关系抽取模型），一种高效且准确的零样本关系分类架构与训练范式。受零样本命名实体识别进展启发，该方法可在一次前向传播中高效、准确地预测多个实体之间的零样本关系标签。在FewRel和WikiZSL基准上的实验表明，该方法在零样本关系分类任务上达到当前最优表现。此外，我们还提出一种合成生成具有多样化关系标签数据集的协议。
原文摘要 · Abstract (English)
We introduce GLiREL (Generalist Lightweight model for zero-shot Relation Extraction), an efficient architecture and training paradigm for zero-shot relation classification. Inspired by recent advancements in zero-shot named entity recognition, this work presents an approach to efficiently and accurately predict zero-shot relationship labels between multiple entities in a single forward pass. Experiments using the FewRel and WikiZSL benchmarks demonstrate that our approach achieves state-of-the-art results on the zero-shot relation classification task. In addition, we contribute a protocol for synthetically-generating datasets with diverse relation labels.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。