Linux/Unix>> TCN-with-attention>> 返回
项目作者： flrngel

项目描述 ：
Character based Temporal Convolutional Networks + Attention Layer
高级语言： Python
项目地址: git://github.com/flrngel/TCN-with-attention.git
创建时间： 2018-04-24T16:25:37Z
项目社区：https://github.com/flrngel/TCN-with-attention
开源协议：
下载


TCN with attention

Temporal Convolutional Network with attention layer

Concept of model is mostly like Simple Neural Attentive Meta-Learner (SNAIL).
But in this model, attention layer is on every top of convolutions layers. And attention size is differ from SNAIL.

Result

Dataset: Agnews without pre-processing

  • with attention: 0.82
  • without attention: 0.81

My thoughts on result

Most of simple models on agnews shows 0.81 accuracy. (Which tested on A Structured Self-Attentive Sentence Embedding, TagSpace and it uses word based embedding)

So 0.82 accuracy with character based model seems worthiness.