← 研踪 PaperTrailarXiv:2611.09342 · v1
Syn2DRE: Synergistic Dual Teacher-Student Framework for Document-level Relation Extraction
首次提交 2026-11-06 19:40
版本更新 2026-11-06 19:40
雷达观测 2026-11-09 11:19
摘要
Document-level Relation Extraction (DocRE) aims to identify relations between entities across a document but typically relies on costly large-scale annotations. While pseudo-labelling enables the use of low-quality data, existing methods often suffer from inefficiency and confirmation bias. To address these challenges, we propose Syn2DRE, a semi-supervised framework that combines self-supervised learning with cross-supervision in a lightweight teacher-student architecture to produce more reliable pseudo-labels. Additionally, we introduce a unified end-to-end training strategy to further improve efficiency of the framework. Experiments on multiple benchmarks show that Syn2DRE consistently outperforms prior state-of-the-art semi-supervised DocRE methods.
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-06 19:40 · 最新观测版本
Syn2DRE: Synergistic Dual Teacher-Student Framework for Document-level Relation Extraction
Document-level Relation Extraction (DocRE) aims to identify relations between entities across a document but typically relies on costly large-scale annotations. While pseudo-labelling enables the use of low-quality data, existing methods often suffer from inefficiency and confirmation bias. To address these challenges, we propose Syn2DRE, a semi-supervised framework that combines self-supervised learning with cross-supervision in a lightweight teacher-student architecture to produce more reliable pseudo-labels. Additionally, we introduce a unified end-to-end training strategy to further improve efficiency of the framework. Experiments on multiple benchmarks show that Syn2DRE consistently outperforms prior state-of-the-art semi-supervised DocRE methods.
查看此版本解读 →查看此版本原文 ↗