A Multi-Task Approach for Improving Biomedical Named Entity Recognition by Incorporating Multi-Granularity information

1 code implementation • Findings (ACL) 2021 • Yiqi Tong, Yidong Chen, Xiaodong Shi

named-entity-recognition Named Entity Recognition +1

一种基于IDLSTM+CRF的中文主地域抽取方法(A Chinese Main Location Extraction Method based on IDLSTM+CRF)

no code implementations • CCL 2021 • Yiqi Tong, PeiGen Ye, Biao Fu, Yidong Chen, Xiaodong Shi

“新闻文本通常会涉及多个地域, 主地域则描述了文本舆情内容的地域属性, 是进行舆情分析的关键属性。目前深度学习领域针对主地域自动抽取的研究还比较少。基于此, 本文构建了一个基于IDLSTM+CRF的主地域抽取系统。该系统通过地名识别、主地域抽取、主地域补全三大模块实现对主地域标签的自动抽取和补全。在公开数据集上的实验结果表明, 我们的方法在地名识别任务上要优于BiLSTM+CRF等模型。而对于主地域抽取任务, 目前还没有标准的中文主地域评测集合。针对该问题, 我们标注并开源了1226条验证集和1500条测试集。最终, 我们的主地域抽取系统在两个集合上分别取得了91. 7%和84. 8%的抽取准确率, 并成功运用于线上生产环境。”

A Comprehensive Survey of Federated Transfer Learning: Challenges, Methods and Applications

no code implementations • 3 Mar 2024 • Wei Guo, Fuzhen Zhuang, Xiao Zhang, Yiqi Tong, Jin Dong

However, since FL enables a continuous share of knowledge among participants with each communication round while not allowing local data to be accessed by other participants, FTL faces many unique challenges that are not present in TL.

Federated Learning Transfer Learning

A Document-Level Neural Machine Translation Model with Dynamic Caching Guided by Theme-Rheme Information

1 code implementation • COLING 2020 • Yiqi Tong, Jiangbin Zheng, Hongkang Zhu, Yidong Chen, Xiaodong Shi

Research on document-level Neural Machine Translation (NMT) models has attracted increasing attention in recent years.

Machine Translation NMT +2