Cooperative Denoising for Distantly Supervised Relation Extraction
文献类型：会议论文
| 作者 | Kai Lei; Daoyuan Chen; Yaliang Li; Nan Du; Min Yang; Wei Fan; Ying Shen |
| 出版日期 | 2018 |
| 会议日期 | 2018 |
| 会议地点 | New Mexico, USA |
| 英文摘要 | Distantly supervised relation extraction greatly reduces human efforts in extracting relational facts from unstructured texts. However, it suffers from noisy labeling problem, which can degrade its performance. Meanwhile, the useful information expressed in knowledge graph is still underutilized in the state-of-the-art methods for distantly supervised relation extraction. In the light of these challenges, we propose CORD, a novel COopeRative Denoising framework, which consists two base networks leveraging text corpus and knowledge graph respectively, and a cooperative module involving their mutual learning by the adaptive bi -directional knowledge distillation and dynamic ensemble with noisy-varying instances. Experimental results on a real-world dataset demonstrate that the proposed method reduces the noisy labels and achieves substantial improvement over the state-of-the-art methods. |
| 语种 | 英语 |
| 源URL | [http://ir.siat.ac.cn:8080/handle/172644/14098]  |
| 专题 | 深圳先进技术研究院_数字所 |
| 推荐引用方式 GB/T 7714 | Kai Lei,Daoyuan Chen,Yaliang Li,et al. Cooperative Denoising for Distantly Supervised Relation Extraction[C]. 见:. New Mexico, USA. 2018. |
入库方式： OAI收割
来源：深圳先进技术研究院
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。