[CONLL2017] Learning local and global contexts using a convolutional recurrent network model
2018-01-08 11:38
453 查看
CNN的优点: can effectively identify coarse-grained local features in a sentence
RNN的优点: are more suited for long-term dependencies(其实是考虑了当前词的上下文)
相关文章推荐
- Human Pose Estimation using Global and Local Normalization
- Agent Inspired Trading Using Recurrent Reinforcement Learning and LSTM Neural Networks
- 论文笔记之:Let there be Color!: Joint End-to-end Learning of Global and Local Image Priors for Automatic
- 吴恩达Deeplearning.ai 第五课 Sequence Model 第一周------Recurrent Neural Network Model
- RCNN学习笔记(8):OverFeat:Integrated Recognition, Localization and Detection using Convolutional Network
- A Tutorial on Deep Learning Part 2: Autoencoders, Convolutional Neural Networks and Recurrent Neural
- Learning and Transferring Mid-Level Image Representations using Convolutional Neural Networks
- PS:Modeling Local and Global Deformations in Deep Learning: Epitomic Convolution...___CVPR2015
- Learning with Local and Global Consistency
- 姿态论文整理--04-Human pose estimation using global and local normalization
- Geometric deep learning on graphs and manifolds using mixture model CNNs
- Let there be Color!: Joint End-to-end Learning of Global and Local Image Priors for Automatic Image
- Asp.Net Globalization and Localization using Local Resource files and Global Resource files
- Learning_and_Transferring_Mid-Level_Image_Representations_using_Convolutional_Neural_Networks
- Learning with local and global consistency阅读报告NIPS2003
- Let there be Color!: Joint End-to-end Learning of Global and Local Image Priors for Automatic Image
- 论文笔记之:Let there be Color!: Joint End-to-end Learning of Global and Local Image Priors for Automatic
- learning and transferring mid-level image representations using convolutional neural networks
- 行人属性“Attribute Recognition by Joint Recurrent Learning of Context and Correlation”
- 论文阅读:Learning and Transferring Mid-Level Image Representations using Convolutional Neural Networks