Topics #

• Biomedical natural language processing
• Deep learning
  • Recurrent neural network
    • Long short-term memory
• Dialog act
• Lexical feature selection
• Word embedding and Sentence embedding
• Sentiment analysis
• String metric
• Topic modeling
  • Latent Dirichlet allocation
• Word segmentation

Books #

• Speech and Language Processing (3rd ed. draft)

Tools and models #

Libraries #

• spaCy
  • textacy: higher-level NLP built on spaCy
• StanfordNLP

• Stanford CoreNLP

• https://github.com/zalandoresearch/flair

• NLTK
• KoNLPy
• http://stackoverflow.com/questions/13466584/korean-language-tokenizer
• Google cloud natural language API
• KenLM
• fastText
• BookNLP
• GluonNLP

Models #

• huggingface/pytorch-transformers - A library of state-of-the-art pretrained models for Natural Language Processing (NLP)
• BERT

Tutorials and talks #

• Natural language understanding by Kyunghyun Cho

Data #

• SQuAD:The Stanford Question Answering Dataset
• http://googleresearch.blogspot.com/2013/12/free-language-lessons-for-computers.html

Courses #

• http://see.stanford.edu/see/courseinfo.aspx?coll=63480b48-8819-4efd-8412-263f1a472f5a by Christopher D. Manning
• https://www.coursera.org/course/nlp
• CS224d: Deep Learning for Natural Language Processing
• Videos: Natural Language Processing with Dan Jurafsky and Chris Manning, 2012
• Videos: Natural language processing with deep learning (winter 2017)
• YSDA course in Natural Language Processing

References #

• http://nlp.stanford.edu/read/

Review #

• Advances in natural language processing

Style #

• Success with Style: Using Writing Style to Predict the Success of Novels - can one predict the successful novels just by style and grammar?

Incoming Links #

Related Articles (Article 0) #

• Biomedical natural language processing
• Computer science
• Convolutional neural network
• Deep learning
• Lexical feature selection
• NLP
• Recurrent neural network
• StanfordNLP
• scispaCy

Suggested Pages #

• 0.189 CNN
• 0.126 Residual Learning
• 0.100 RNN
• 0.085 Text analysis
• 0.069 Pointwise mutual information
• 0.055 Residual leanrning
• 0.052 Machine learning
• 0.041 Research advices
• 0.032 Meta learning
• 0.024 Tomas Mikolov
• More suggestions...