- lecture slides
- Our lecture videos (russian): lecture, seminar
- Stanford NLP lecture: text convolutions
Seminar colab url
Your task for this week is to get past two notebooks: ./homework_part1.ipynb and... you guessed it, ./homework_part2.ipynb.
The second part of homework requires you to train a deep neural network. See ./seminar.ipynb for problem description, tips and tricks.
- Colah's blog on convolutions, including text convolutions - url
- Same architectures applied for music - blog post
-
A Unified Architecture for Natural Language Processing: Deep Neural Networks with Multitask Learning Collobert et al. 2008 [pdf]
-
Bag of Tricks for Efficient Text ClassificationJoulin et al. 2016 [arxiv]
-
Convolutional Neural Networks for Sentence Classification Yoon Kim, 2014 [arxiv]
-
Character-level Convolutional Networks for Text Classification Zhang et al., 2015 [arxiv]
-
A Sensitivity Analysis of (and Practitioners' Guide to) Convolutional Neural Networks for Sentence Classification Zhang et al., 2015 [arxiv]
-
Self-Adaptive Hierarchical Sentence Model Zhao et al., 2015 [arxiv]
-
Very Deep Convolutional Networks for Text Classification Conneau et al., 2016 [arxiv]
-
Supervised Learning of Universal Sentence Representations from Natural Language Inference Data Conneau et al., 2017 [arxiv]
-
Recurrent Neural Network for Text Classification with Multi-Task Learning Liu et al., 2016 [arxiv]
-
Document Modeling with Gated Recurrent Neural Network for Sentiment Classification Tang et al., 2015[pdf]
-
Efficient Character-level Document Classification by Combining Convolution and Recurrent Layers Xiao et al., 2015 [arxiv]
-
A C-LSTM Neural Network for Text Classification Zhout et al., 2015 [arxiv]
-
Recurrent Convolutional Neural Networks for Text Classification Lai et al. 2015 [pdf]
-
Comparative Study of CNN and RNN for Natural Language Processing Yin et al., 2017 [arxiv]