当前位置: X-MOL 学术J. Web Semant. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Curriculum learning for distant supervision relation extraction
Journal of Web Semantics ( IF 2.5 ) Pub Date : 2020-02-29 , DOI: 10.1016/j.websem.2020.100559
Qiongxin Liu , Peng Wang , Jiasheng Wang , Jing Ma

Relation extraction under distant supervision leverages the existing knowledge base to label data automatically, thus greatly reduced the consumption of human labors. Although distant supervision is an efficient method to obtain a large amount of labeled data, the training dataset labeled by distant supervision suffers from noise problem resulting in poor generalization ability of the relation extractor. To alleviate the noise problem, we propose a novel relation extraction method based on curriculum learning. Curriculum learning is utilized to guide the training process of relation extractor, specifically through the predefined curriculum-driven mentor network. Mentor network can dynamically adjust the weights of sentences during training, giving lower weights to noisy sentences and higher weights to truly labeled sentences. Relation extractor and mentor network are trained collaboratively to optimize joint objective. The experimental results show that the proposed method can improve the generalization ability of relation extractor in a noisy environment and obtains better performance for relation extraction.



中文翻译:

远程监督关系提取中的课程学习

远程监督下的关系提取利用现有知识库自动标记数据,从而极大地减少了人工的消耗。尽管远程监管是一种获取大量标记数据的有效方法,但是由远程监管标记的训练数据集存在噪声问题,导致关系提取器的泛化能力较差。为了缓解噪声问题,我们提出了一种基于课程学习的新的关系提取方法。课程学习用于指导关系提取器的培训过程,特别是通过预定义的课程驱动的导师网络进行。指导者网络可以在训练过程中动态调整句子的权重,从而为嘈杂的句子赋予较低的权重,为真正带有标签的句子赋予较高的权重。关系提取器和指导者网络经过协作培训以优化联合目标。实验结果表明,该方法可以提高嘈杂环境中关系提取器的泛化能力,并具有较好的关系提取性能。

更新日期:2020-02-29
down
wechat
bug