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。”
1 code implementation • 25 Dec 2023 • Rui Zhao, Liang Zhang, Biao Fu, Cong Hu, Jinsong Su, Yidong Chen
The first KL divergence optimizes the conditional variational autoencoder and regularizes the encoder outputs, while the second KL divergence performs a self-distillation from the posterior path to the prior path, ensuring the consistency of decoder outputs.
no code implementations • 20 Jul 2023 • Yafang Zheng, Lei Lin, Shuangtao Li, Yuxuan Yuan, Zhaohong Lai, Shan Liu, Biao Fu, Yidong Chen, Xiaodong Shi
Inspired by this, we propose LRF, a novel \textbf{L}ayer-wise \textbf{R}epresentation \textbf{F}usion framework for CG, which learns to fuse previous layers' information back into the encoding and decoding process effectively through introducing a \emph{fuse-attention module} at each encoder and decoder layer.
no code implementations • 20 May 2023 • Lei Lin, Shuangtao Li, Yafang Zheng, Biao Fu, Shan Liu, Yidong Chen, Xiaodong Shi
There is mounting evidence that one of the reasons hindering CG is the representation of the encoder uppermost layer is entangled, i. e., the syntactic and semantic representations of sequences are entangled.
1 code implementation • 14 Mar 2023 • Biao Fu, Minpeng Liao, Kai Fan, Zhongqiang Huang, Boxing Chen, Yidong Chen, Xiaodong Shi
A popular approach to streaming speech translation is to employ a single offline model with a wait-k policy to support different latency requirements, which is simpler than training multiple online models with different latency constraints.
1 code implementation • 11 Apr 2022 • Biao Fu, PeiGen Ye, Liang Zhang, Pei Yu, Cong Hu, Yidong Chen, Xiaodong Shi
Sign Language Translation (SLT) is a promising technology to bridge the communication gap between the deaf and the hearing people.
Ranked #7 on Sign Language Translation on CSL-Daily