Zero-shot User Intent Detection via Capsule Neural Networks

  • Architecture

   

   

Zero-shot User Intent Detection via Capsule Neural Networks

   

   

  • SemanticCaps

    通过Bi-LSTM表征得到的隐层向量经过multi-head后可以得到R个表征

    Zero-shot User Intent Detection via Capsule Neural Networks

       

    Zero-shot User Intent Detection via Capsule Neural Networks

       

    Zero-shot User Intent Detection via Capsule Neural Networks

   

  • DetectionCaps

    这部分和一般的胶囊网络一样，除了loss function中加入了self attention部分

       

    Zero-shot User Intent Detection via Capsule Neural Networks

       

    Zero-shot User Intent Detection via Capsule Neural Networks

       

    Zero-shot User Intent Detection via Capsule Neural Networks

       

    Zero-shot User Intent Detection via Capsule Neural Networks

       

    Zero-shot User Intent Detection via Capsule Neural Networks

   

   

  • Zero-shot DetectionCaps

   

基本过程和DetectionCaps很相似,计算DetectionCaps中已存在的existing intent和当前inference阶段emerging intent的相似度q,然后加权求和，squash后得到activation vector进行分类

Zero-shot User Intent Detection via Capsule Neural Networks

   

Zero-shot User Intent Detection via Capsule Neural Networks

   

   

Zero-shot User Intent Detection via Capsule Neural Networks

   

   

   

   

   

   

相关文章：

  • 2021-09-27
  • 2021-09-13
  • 2021-12-22
  • 2021-06-06
  • 2021-09-08
  • 2021-11-28
猜你喜欢
  • 2021-12-12
  • 2021-07-06
  • 2021-08-05
  • 2022-01-10
  • 2021-07-05
  • 2021-08-01
  • 2019-11-28
相关资源
相似解决方案
热门标签
Java Python linux javascript Mysql C# Docker 算法 前端 SpringBoot Redis Vue spring 设计模式 .net core .net kubernetes c++ 数据库 数据结构 大数据 js 机器学习 微服务 Android Go 程序员 面试 JVM ASP.net core 云原生 人工智能 后端 PHP git CSS golang k8s Nginx Django mybatis 深度学习 多线程 React 架构 devops 爬虫 云计算 Spring Boot LeetCode