通过结构化语义相似性挑选示例，提升少样本关系抽取效果
Structured Semantic Information Helps Retrieve Better Examples for In-Context Learning Applied to Few-Shot Relation Extraction
- 基于句法语义结构相似性自动选例，增强示例多样性
- 混合策略在FS-TACRED上达最新水平，FewRel子集显著提效
- 跨数据集与模型族表现稳定，适合少样本关系抽取场景
本文提出多种自动获取额外示例的策略，将关系抽取从1样本提升至少样本设置。核心是引入一种新示例选择方法：根据潜在句法-语义结构与给定1样本示例的相似性进行筛选。该方法产生的示例在词汇和句子结构上与大模型生成的互补。当二者结合时，混合系统能更全面刻画目标关系。该框架在FS-TACRED和FS-FewRel数据集上均表现良好，适配Qwen与Gemma系列大模型。整体上，混合系统持续优于其他策略，在FS-TACRED上达到当前最优性能，在定制化的FewRel子集上实现显著提升。
原文摘要 · Abstract (English)
This paper presents several strategies to automatically obtain additional examples for in-context learning, effectively transforming relation extraction from a 1-shot to a few-shot setting. Specifically, we introduce a novel strategy for example selection, in which new examples are selected based on the similarity of their underlying syntactic-semantic structure to the provided 1-shot example. We show that our strategy results in complementary word choices and sentence structures compared to LLM-generated examples. When both strategies are combined, the resulting hybrid system achieves a more holistic picture of the relations of interest than either method alone. Our framework transfers well across datasets (FS-TACRED and FS-FewRel) and LLM families (Qwen and Gemma). Overall, our hybrid system consistently outperforms alternative strategies achieving state-of-the-art performance on FS-TACRED and strong gains on a customized FewRel subset.
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。