Giter VIP home page Giter VIP logo

comment's Introduction

comment

comment's People

Contributors

dwykat avatar

comment's Issues

句子单词之间解析距离的计算 | Mission

https://dwykat.github.io/blog/2018/11/14/depdist-post/

最近在读aspect-level情感分类论文的时候,看到一个attention机制的改进,实现起来比较有意思,做一下记录。通常,我们在对句子做attention的时候,对句子中的每个单词都是同等看待的,attention得到的结果再作用到每个单词的隐层表示上去,作为权重。而在方面级情感分类中,针对一个特定方面,不同位置的单词显然作用是有差别的,因此就有了基于与aspect words距离的权重设计,但还是考虑了句子的所有单词,这篇论文的作者则更进一步,直接基于解析距离来做,设置距离阈值,大于该阈值的直接不考虑(即权重为0),取得了不错的效果,那么该怎么计算呢?

cs224n lecture 2 note:word vectors | Mission

https://dwykat.github.io/blog/2018/11/04/cs224n-lecture2/

  1. 为什么要使用word embedding? 在信号处理领域,图像和音频信号的输入往往是表示成高维度、密集的向量形式,在图像和音频的应用系统中,如何对输入信息进行编码显得非常重要和关键,这将直接决定了系统的质量。在自然语言处理中也类似,传统做法是给单词标号,每个词表示为index处为1,其他位置为0,总长度为词表大小的one-hot形式,这样做有很明显的缺点,如下所示。 词语直接缺乏关联 难以存储和维护 难以计算词语相似度

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.