comment's Introduction
comment's People
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 4 note: word win clf and nn | Mission
https://dwykat.github.io/blog/2018/11/18/cs224n-lecture4/
这节课介绍了根据窗口内上下文预测单词的分类问题,由此引入了softmax, hinge loss, cross entropy等函数,最后,详细推导了神经网络反向传播过程。
cs224n lecture 6 note: dependency parsing | Mission
cs224n lecture 4 note: word win clf and nn | Mission
https://dwykat.github.io/blog/2018/11/18/cs224n-lecture-4/
这节课介绍了根据窗口内上下文预测单词的分类问题,由此引入了softmax, hinge loss, cross entropy等函数,最后,详细推导了神经网络反向传播过程。
cs224n lecture 5 note: explanation for backpropagation | Mission
https://dwykat.github.io/blog/2018/12/02/cs224n-lecture5/
终于忙完开题一切事宜,继续学习斯坦福公开课。
cs224n lecture 2 note:word vectors | Mission
https://dwykat.github.io/blog/2018/11/04/cs224n-lecture2/
- 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
cs224n lecture 8 note: recurrent neural network | Mission
cs224n lecture 7 note: tensorflow | Mission
cs224n lecture 1 note: introduction | Mission
https://dwykat.github.io/blog/2018/10/28/cs224n-lecture1/
- What is NLP? 自然语言处理是计算机科学、人工智能和语言学的交叉领域,旨在让计算机能够“理解”或处理自然语言,而重点就是计算机对自然语言的处理,这就延伸出了很多应用。
cs224n lecture 3 note: more word vectors | Mission
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
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.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.