DiffIE：基于扩散模型的开放信息抽取
DiffIE: Diffusion-based Open Information Extraction
- Matrosov Institute for System Dynamics and Control Theory, SB RAS（俄罗斯科学院西伯利亚分院马特罗夫系统动力学与控制理论研究所）
- AI Talent Hub, ITMO University（ITMO大学AI人才中心）
- MWS AI
- Trusted AI Research Center, RAS（俄罗斯科学院可信人工智能研究中心）
- IITU University（IITU大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
DiffIE是基于扩散模型的开放信息抽取方法，通过独立反向扩散轨迹生成候选三元组池，在多个公开基准上达到最优性能，为多输出结构化预测提供了有效机制。
AI中文摘要：
单个句子通常表达多个有效的关系三元组，这使得开放信息抽取（OpenIE）本质上是一个多输出任务。现有的神经系统通过自回归生成处理该任务，该方法灵活但速度慢且易产生冗余；或通过固定槽位预测处理，该方法高效但将抽取预算与训练绑定。我们引入DIFFIE，它将条件离散扩散的随机性本身作为抽取机制：对每个 token 的角色标签进行独立的反向扩散轨迹，生成候选三元组池，该池在宽松匹配下聚类并排序形成输出。池大小和返回的抽取数量是推理时的选择，将抽取预算与训练解耦，并将测试时的计算暴露为可调维度。DIFFIE在CaRB（1-1）的F1值和AUC上均达到新的最优水平，在BenchIE中优于最强的基于规则的系统ClausIE；在标准CaRB和WiRe57评估中也保持竞争力，在报告所有四个基准的系统中取得最佳平均分数。 ablation实验显示，在我们的设定中，均匀离散扩散优于吸收状态扩散，且匹配的非扩散随机标注器无法复现其增益。我们的结果表明，扩散随机性是处理具有多个有效输出的结构化预测任务的有效机制。
英文摘要：
A single sentence often expresses multiple valid relational triplets, which makes Open Information Extraction (OpenIE) fundamentally a multi-output task. Existing neural systems handle this by autoregressive generation, which is flexible but slow and prone to redundancy, or by fixed-slot prediction, which is efficient but couples the extraction budget to training. We introduce DIFFIE which instead treats the stochasticity of conditional discrete diffusion as the extraction mechanism itself: independent reverse-diffusion trajectories over per-token role tags produce a pool of candidate triplets, which are clustered under lenient matching and ranked to form the output. Both the pool size and the number of returned extractions are inference-time choices, decoupling the extraction budget from training and exposing test-time compute as a tunable axis. DIFFIE achieves the new state of the art in CaRB (1-1) both F1 and AUC, and outperforms the strongest rule-based system (ClausIE) in BenchIE; it also remains competitive in standard CaRB and WiRe57 evaluations, giving the best average score among systems that report all four benchmarks. Ablations show that uniform discrete diffusion outperforms absorbing state diffusion in our setting, and that a matched non-diffusion stochastic tagger does not reproduce its gains. Our results indicate that diffusion stochasticity is an effective mechanism for structured prediction tasks with multiple valid outputs.
