Knowledge Commons of Institute of Automation,CAS
Distantly Supervised Relation Extraction in Federated Settings | |
Sui DB(隋典伯)1,2; Yubo Chen1,2; Kang Liu1,2; Jun Zhao1,2 | |
2021-11 | |
会议名称 | Findings of the Association for Computational Linguistics: EMNLP 2021 |
会议日期 | 2021 |
会议地点 | Punta Cana, Dominican Republic |
摘要 | In relation extraction, distant supervision is widely used to automatically label a large-scale training dataset by aligning a knowledge base with unstructured text. Most existing studies in this field have assumed there is a great deal of centralized unstructured text. However, in practice, texts are usually distributed on different platforms and cannot be centralized due to privacy restrictions. Therefore, it is worthwhile to investigate distant supervision in the federated learning paradigm, which decouples the training of the model from the need for direct access to raw texts. However, overcoming label noise of distant supervision becomes more difficult in federated settings, because texts containing the same entity pair scatter around different platforms. In this paper, we propose a federated denoising framework to suppress label noise in federated settings. The key of this framework is a multiple instance learning based denoising method that is able to select reliable sentences via cross-platform collaboration. Various experiments on New York Times dataset and miRNA gene regulation relation dataset demonstrate the effectiveness of the proposed method. |
语种 | 英语 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/48932 |
专题 | 多模态人工智能系统全国重点实验室_自然语言处理 |
作者单位 | 1.National Laboratory of Pattern Recognition, Institute of Automation, CAS 2.School of Artificial Intelligence, University of Chinese Academy of Sciences |
第一作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Sui DB,Yubo Chen,Kang Liu,et al. Distantly Supervised Relation Extraction in Federated Settings[C],2021. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
2021.findings-emnlp.(773KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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。
修改评论