Abstract
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.
Abstract (translated)
从自然语言构建知识图谱需要从复杂、信息密集的句子中提取结构化三元组。本文研究了将文本分解为原子命题（最小、语义自足的信息单元）是否能改进三元组抽取。我们引入了MPropositionneur-V2，一个覆盖六种欧洲语言的小型多语言模型，通过将Qwen3-32B的知识蒸馏至Qwen3-0.6B架构中进行训练，并评估了其整合到两种抽取范式中的效果：以实体为中心（GLiREL）和生成式（Qwen3）。在SMiLER、FewRel、DocRED和CaRB上的实验表明，原子命题有益于较弱的抽取器（GLiREL、CoreNLP、0.6B模型），提高了关系召回率，并在多语言设置中提升了整体准确率。对于更强大的大语言模型，一种回退组合策略在保持关系抽取增益的同时，恢复了实体召回率的损失。这些结果表明，原子命题是一种可解释的中间数据结构，能够补充而非替代抽取器。
URL
https://arxiv.org/abs/2604.02866
