structured_self_attention_sent_embedding
refer: https://arxiv.org/pdf/1703.03130.pdf
1. 处理query-pair的相似度问题, 输入文件每行格式为: query1tquery2tscore; 问题等价时score=1.0否则score=0.0
1. 输入层使用字符粒度的向量 2. 隐藏层使用self-attention对query进行encoder 3. 使用attention-metrix对query进行编码
上一篇:StructuredSelfAttentionTensorflow
下一篇:weakly-supervised-detector
还没有评论,说两句吧!
热门资源
seetafaceJNI
项目介绍 基于中科院seetaface2进行封装的JAVA...
spark-corenlp
This package wraps Stanford CoreNLP annotators ...
Keras-ResNeXt
Keras ResNeXt Implementation of ResNeXt models...
capsnet-with-caps...
CapsNet with capsule-wise convolution Project ...
inferno-boilerplate
This is a very basic boilerplate example for pe...
智能在线
400-630-6780
聆听.建议反馈
E-mail: support@tusaishared.com