Search Results for author:
Found 7 papers, 4 papers with code
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)
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%。
Understanding Parameter Sharing in Transformers
Inspired by this, we tune the training hyperparameters related to model convergence in a targeted manner.
MobileNMT: Enabling Translation in 15MB and 30ms
With the co-design of model and engine, compared with the existing system, we speed up 47. 0x and save 99. 5% of memory with only 11. 6% loss of BLEU.
LightSeq2: Accelerated Training for Transformer-based Models on GPUs
In this paper, we present LightSeq2, a system to accelerate training for a general family of Transformer models on GPUs.
LightSeq: A High Performance Inference Library for Transformers
Transformer, BERT and their variants have achieved great success in natural language processing.
Multi-Task Reinforcement Learning based Mobile Manipulation Control for Dynamic Object Tracking and Grasping
Tracking and grasping a dynamic object with a random trajectory is even harder.
An Efficient Agreement Mechanism in CapsNets By Pairwise Product
Capsule networks (CapsNets) are capable of modeling visual hierarchical relationships, which is achieved by the "routing-by-agreement" mechanism.
