SelfLRE: Self-refining Representation Learning for Low-resource Relation Extraction
SelfLRE: Self-refining Representation Learning for Low-resource Relation Extraction
复制标题
DOI：
10.1145/3539618.3592058
复制
发表时间：
2023-07
期刊：
影响因子：
--
通讯作者：
Xuming Hu;Junzhe Chen;Shiao Meng;Lijie Wen;Philip S. Yu
中科院分区：
文献类型：
--
作者：
Xuming Hu;Junzhe Chen;Shiao Meng;Lijie Wen;Philip S. Yu
低资源关系抽取（LRE）旨在从有限的标注语料中抽取潜在的关系，以解决人工标注不足的问题。以往的研究主要包括两类方法：（1）自我训练方法，通过模型的预测来改进自己，从而在预测错误时遭受确认偏差。(2)因此，学习任务不可知表示的自集成方法通常不能很好地用于特定任务。在我们的工作中，我们提出了一种新的LRE架构名为SelfLRE，它利用两个互补的模块，一个模块使用自训练来获得未标记数据的伪标签，另一个模块使用自集成学习来获得任务不可知的表示，并利用现有的伪标签来改进未标记数据的更好的特定于任务的表示。两个模型通过多任务学习进行联合训练，以迭代提高LRE任务的效果。在三个公共数据集上的实验表明，SelfLRE比SOTA基线实现了1.81%的性能提升。源代码可在https://github.com/THU-BPM/SelfLRE上获得。
Low-resource relation extraction (LRE) aims to extract potential relations from limited labeled corpus to handle the problem of scarcity of human annotations. Previous works mainly consist of two categories of methods: (1) Self-training methods, which improve themselves through the models' predictions, thus suffering from confirmation bias when the predictions are wrong. (2) Self-ensembling methods, which learn task-agnostic representations, therefore, generally do not work well for specific tasks. In our work, we propose a novel LRE architecture named SelfLRE, which leverages two complementary modules, one module uses self-training to obtain pseudo-labels for unlabeled data, and the other module uses self-ensembling learning to obtain the task-agnostic representations, and leverages the existing pseudo-labels to refine the better task-specific representations on unlabeled data. The two models are jointly trained through multi-task learning to iteratively improve the effect of LRE task. Experiments on three public datasets show that SelfLRE achieves 1.81% performance gain over the SOTA baseline. Source code is available at: https://github.com/THU-BPM/SelfLRE.