A comprehensive survey of deep learning applications in NLP
Two papers are included:
- A Primer on Neural Network Models for Natural Language Processing (Goldberg Y. A Primer on Neural Network Models for Natural Language Processing[J]. J. Artif. Intell. Res.(JAIR), 2016, 57: 345-420.)
This paper describe major concepts in deep learning: MLP, bp algorithm, neural network training technology include dropout, batch norm and regularization, loss function, CNN, RNN, LSTM, Recursive Neural Networn and word embedding. It is a good introduction to deep learning and basic applications of deep learning in NLP.
- Recent Trends in Deep Learning Based Natural Language Processing (Young T, Hazarika D, Poria S, et al. Recent trends in deep learning based natural language processing[J]. arXiv preprint arXiv:1708.02709, 2017.)
This paper gives a comprehensive survey of state-of-art deep learning in NLP. Topics inlude: word embedding, CNN, RNN, Recursive Neural Network, reinforced models, unsupervised models include GAN, memory augmented network and their apllications in NLP tasks. Those NLP tasks include: Word Segmentation, POS tagging, Named Entity recognition, Dependency parsing, Classification, Language Modeling, Natural Language Generation, Image Caption, QA, Machine Translation, Dialogue and Sentiment analysis.