用原子命题分解文本，提升弱提取器的三元组抽取效果
LLM-based Atomic Propositions help weak extractors: Evaluation of a Propositioner for triplet extraction
- 将句子拆解为最小语义单元（原子命题）辅助抽取
- 弱提取器在多个数据集上关系召回率显著提升
- 适合资源受限场景或需可解释性的知识图谱构建
从自然语言构建知识图谱需要从复杂密集的句子中抽取结构化三元组。本文探究将文本分解为原子命题（语义独立的最小信息单元）是否能提升三元组抽取性能。我们提出MPropositionneur-V2，一个基于Qwen3-32B通过知识蒸馏得到的小型多语言模型（覆盖六种欧洲语言），其架构为Qwen3-0.6B。评估其在两种抽取范式中的表现：以实体为中心（GLiREL）和生成式（Qwen3）。在SMiLER、FewRel、DocRED和CaRB数据集上的实验表明，原子命题有助于较弱的提取器（GLiREL、CoreNLP、0.6B模型），提升了关系召回率，并在多语言设置下提高整体准确率。对于更强的LLM，采用回退组合策略，在保持关系抽取优势的同时恢复实体召回损失。结果表明，原子命题是一种可解释的中间数据结构，能有效补充而非替代现有抽取器。
原文摘要 · Abstract (English)
Knowledge Graph construction from natural language requires extracting structured triplets from complex, information-dense sentences. In this paper, we investigate if the decomposition of text into atomic propositions (minimal, semantically autonomous units of information) can improve the triplet extraction. We introduce MPropositionneur-V2, a small multilingual model covering six European languages trained by knowledge distillation from Qwen3-32B into a Qwen3-0.6B architecture, and we evaluate its integration into two extraction paradigms: entity-centric (GLiREL) and generative (Qwen3). Experiments on SMiLER, FewRel, DocRED and CaRB show that atomic propositions benefit weaker extractors (GLiREL, CoreNLP, 0.6B models), improving relation recall and, in the multilingual setting, overall accuracy. For stronger LLMs, a fallback combination strategy recovers entity recall losses while preserving the gains in relation extraction. These results show that atomic propositions are an interpretable intermediate data structure that complements extractors without replacing them.
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。