“Text-2014-12-18”版本间的差异
来自cslt Wiki
（→CNN in NLP） |
（→blog） |
||
| （相同用户的3个中间修订版本未显示） | |||
| 第11行： | 第11行： | ||
* Learning Semantic Representations Using Convolutional Neural Networks for Web Search[http://wwwconference.org/proceedings/www2014/companion/p373.pdf] | * Learning Semantic Representations Using Convolutional Neural Networks for Web Search[http://wwwconference.org/proceedings/www2014/companion/p373.pdf] | ||
* Convolutional Neural Networks for Sentence Classification[https://files.nyu.edu/yhk255/public/data/Kim_EMNLP_2014.pdf](EMNLP2014) | * Convolutional Neural Networks for Sentence Classification[https://files.nyu.edu/yhk255/public/data/Kim_EMNLP_2014.pdf](EMNLP2014) | ||
| + | * Relation Classification via Convolutional Deep Neural Network.“ COLING 2014 Best Paper[http://www.nlpr.ia.ac.cn/cip/liukang.files/coling2014.pdf] | ||
| + | |||
==cnn code== | ==cnn code== | ||
* Convolutional Neural Networks (LeNet) [http://deeplearning.net/tutorial/lenet.html] | * Convolutional Neural Networks (LeNet) [http://deeplearning.net/tutorial/lenet.html] | ||
| + | ==blog== | ||
| + | * Neural Networks (Deep Learning) , NLP and Text Mining[http://www.zhizhihu.com/html/y2014/4662.html]ppt[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/e/ea/PijiLi-dl-tm.pdf] | ||
| + | :* it is a good summary for word2vec in nlp from 香港中文大学 | ||
2014年12月18日 (四) 03:55的最后版本
CNN in NLP
meeting ppt
Conference PPT
- EMNLP2014 Convolutional Neural Networks for Sentence Classi�cation [1]
- NIPS2014 PPT(Natural Language Understanding in a Continuous Space)[2]
- A Convolutional Neural Network for Modelling Sentences [3](acl2014)
- Convolutional Neural Network Architectures for Matching Natural Language Sentences[4](nips 2014)
- Learning Semantic Representations Using Convolutional Neural Networks for Web Search[5]
- Convolutional Neural Networks for Sentence Classification[6](EMNLP2014)
- Relation Classification via Convolutional Deep Neural Network.“ COLING 2014 Best Paper[7]
cnn code
- Convolutional Neural Networks (LeNet) [8]
blog
- it is a good summary for word2vec in nlp from 香港中文大学
