基于Self-Attention的句法感知汉语框架语义角色标注(Syntax-Aware Chinese Frame Semantic Role Labeling Based on Self-Attention)

no code implementations • CCL 2020 • Xiaohui Wang, Ru Li, Zhiqiang Wang, Qinghua Chai, Xiaoqi Han

框架语义角色标注(Frame Semantic Role Labeling, FSRL)是基于FrameNet标注体系的语义分析任务。语义角色标注通常对句法有很强的依赖性, 目前的语义角色标注模型大多基于双向长短时记忆网络Bi-LSTM, 虽然可以获取句子中的长距离依赖信息, 但无法很好获取句子中的句法信息。因此, 引入self-attention机制来捕获句子中每个词的句法信息。实验结果表明, 该模型在CFN(Chinese FrameNet, 汉语框架网)数据集上的F1达到83. 77%, 提升了近11%。

Semantic Role Labeling

LightSeq2: Accelerated Training for Transformer-based Models on GPUs

1 code implementation • 12 Oct 2021 • Xiaohui Wang, Yang Wei, Ying Xiong, Guyue Huang, Xian Qian, Yufei Ding, Mingxuan Wang, Lei LI

In this paper, we present LightSeq2, a system to accelerate training for a general family of Transformer models on GPUs.

Machine Translation Speech Recognition +1

LightSeq: A High Performance Inference Library for Transformers

1 code implementation • NAACL 2021 • Xiaohui Wang, Ying Xiong, Yang Wei, Mingxuan Wang, Lei LI

Transformer, BERT and their variants have achieved great success in natural language processing.

Machine Translation Translation

Multi-Task Reinforcement Learning based Mobile Manipulation Control for Dynamic Object Tracking and Grasping

no code implementations • 7 Jun 2020 • Cong Wang, Qifeng Zhang, Qiyan Tian, Shuo Li, Xiaohui Wang, David Lane, Yvan Petillot, Ziyang Hong, Sen Wang

Tracking and grasping a dynamic object with a random trajectory is even harder.

Object Tracking reinforcement Learning

An Efficient Agreement Mechanism in CapsNets By Pairwise Product

1 code implementation • 1 Apr 2020 • Lei Zhao, Xiaohui Wang, Lei Huang

Capsule networks (CapsNets) are capable of modeling visual hierarchical relationships, which is achieved by the "routing-by-agreement" mechanism.