Abstract
Universal Information Extraction (UIE) has garnered significant attention due to its ability to address model explosion problems effectively. Extractive UIE can achieve strong performance using a relatively small model, making it widely adopted. Extractive UIEs generally rely on task instructions for different tasks, including single-target instructions and multiple-target instructions. Single-target instruction UIE enables the extraction of only one type of relation at a time, limiting its ability to model correlations between relations and thus restricting its capability to extract complex relations. While multiple-target instruction UIE allows for the extraction of multiple relations simultaneously, the inclusion of irrelevant relations introduces decision complexity and impacts extraction accuracy. Therefore, for multi-relation extraction, we propose LDNet, which incorporates multi-aspect relation modeling and a label drop mechanism. By assigning different relations to different levels for understanding and decision-making, we reduce decision confusion. Additionally, the label drop mechanism effectively mitigates the impact of irrelevant relations. Experiments show that LDNet outperforms or achieves competitive performance with state-of-the-art systems on 9 tasks, 33 datasets, in both single-modal and multi-modal, few-shot and zero-shot settings.\footnote{this https URL}
Abstract (translated)
通用信息抽取（UIE）因其能够有效解决模型爆炸问题而备受关注。提取型UIE能够在使用相对较小的模型的情况下取得强劲性能，因此被广泛采用。提取型UIEs通常依赖于不同的任务指令，包括单目标和多目标指令。单一目标指令UIE一次只能提取一种关系类型，这限制了它建模关系之间关联的能力，并且限制了其抽取复杂关系的能力。虽然多目标指令UIE可以同时提取多种关系，但包含不相关的关系会增加决策的复杂性并影响提取精度。因此，对于多关系抽取，我们提出了LDNet（Label Drop Network），该模型集成了多方面关系建模和标签丢弃机制。通过将不同关系分配给不同的层级进行理解和决策，我们可以减少决策混乱。此外，标签丢弃机制有效地缓解了不相关关系的影响。实验表明，在单模式、多模式、少样本以及零样本设置下，LDNet在9个任务、33个数据集上表现优于或与最先进的系统相当。\footnote{此链接指向相关信息源}
URL
https://arxiv.org/abs/2502.12614
