Comments (7)
看了下NLP的部分,简直太差了,比如什么是文本挖掘,第一句话说完了别人还是不知道啥意思,比如句法分析,这个定义压根没说清楚句法分析在干嘛吗...比如文本分类,堆一堆网络名称在这里没啥意义,另外,谁说最好的时bilstm了...为什么文本的特征工程放的那么靠后,前面讲了一堆应用包括文本分类都是依赖文本的特征工程的啊,文本特征工程的分类也不好,显然应该从explicit和implicit的角度来分,explicit包括ngram这种,还有利用KB的比如esa或者这些lexicon feature,implicit也应该讲word (word2vec, glove)/doc (para2vec, DSSM, skip-thought, etc.)的embedding方法,甚至延申到一些network embedding (LINE, DeepWalk, PTE, etc.)。把BERT单独拿出来和elmo比较是为何...Attention这种里程碑的东西讲得太太敷衍了...
总的来说,这些内容像是一个长期阅读各种AI公众号和博客的人写的,很浮夸,没有任何实践和理解总结。如果就这样出了书,真的非常误人子弟,强烈希望作者能够再更大的渠道召集些各方面的一线工作人员来编写各个部分...
from deeplearning-500-questions.
看了下NLP的部分,简直太差了,比如什么是文本挖掘,第一句话说完了别人还是不知道啥意思,比如句法分析,这个定义压根没说清楚句法分析在干嘛吗...比如文本分类,堆一堆网络名称在这里没啥意义,另外,谁说最好的时bilstm了...为什么文本的特征工程放的那么靠后,前面讲了一堆应用包括文本分类都是依赖文本的特征工程的啊,文本特征工程的分类也不好,显然应该从explicit和implicit的角度来分,explicit包括ngram这种,还有利用KB的比如esa或者这些lexicon feature,implicit也应该讲word (word2vec, glove)/doc (para2vec, DSSM, skip-thought, etc.)的embedding方法,甚至延申到一些network embedding (LINE, DeepWalk, PTE, etc.)。把BERT单独拿出来和elmo比较是为何...Attention这种里程碑的东西讲得太太敷衍了...
总的来说,这些内容像是一个长期阅读各种AI公众号和博客的人写的,很浮夸,没有任何实践和理解总结。如果就这样出了书,真的非常误人子弟,强烈希望作者能够再更大的渠道召集些各方面的一线工作人员来编写各个部分...
点开参考文献看了下,果然是各种博客...国内AI有多浮躁可见一斑...
from deeplearning-500-questions.
如需要帮助编辑MD版本,我可提供力所能及的帮助,可联系[email protected]
from deeplearning-500-questions.
加微信Tan:tan_weixin88
from deeplearning-500-questions.
如果是CV方向更佳
from deeplearning-500-questions.
乐意帮忙,微信LYC2014qd,邮箱 [email protected]
from deeplearning-500-questions.
@zhujiangang 各位重要贡献者都是在尽力去帮助大家, 查找资料本就是一件费心费力的事, 还是要大家多交流, 帮助这个优秀的项目不断改进.
from deeplearning-500-questions.
Related Issues (20)
- 好多公式都不能正常显示,通篇都是$符号!! HOT 8
- 目录预览与内容对不上
- 您好 请问能否提供京东外的购书渠道 我所在地区短期内无货 很喜欢您的书
- 第九章部分图片缺失
- Translations: tool proposal
- 公式不能正常显示,应该怎么做? HOT 8
- 算法岗校招内推
- DeepLearning
- 深度学习五百问
- My professor assigned to find objective and named the project .As there is three self driving car ,now the question is to find objective and find some appropriate of project .For example in this project my own objective is
- 使用方法,公式不能显示解决方法
- Deep learning
- 真的有500问吗?
- “纠错” HOT 4
- 第三章激活函数
- aodv-uu过来的 HOT 5
- 第二章机器学习基础.md文件中2.13章节中有几个三级标题序号出错 HOT 1
- Questions HOT 5
- Add OSSF Scorecard security workflow HOT 4
- 2.3-2.7章节在哪里? HOT 11
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.
from deeplearning-500-questions.