Project-Related Reference Material for CS 175

CS 175, Winter 2017
Below are links to suggested reading organized by topic. If you are doing a project on any of these topics (or interested in potentially doing a project on these topics) then these online resources should be helpful.

Text Classification
Chapter on text classification and naive Bayes from Manning et al
Chapter on vector-based classification for text from Manning et al
Chapter on logistic regression for document classification from Jurafsky and Martin
Comprehensive survey paper on text classification algorithms by Aggarwal and Zhai (2012)
Overview of general principles in machine learning from Goodfellow et al (2016)
Detailed review of neural networks for natural language and text analysis by Goldberg (2015)
Tutorial paper on multi-label classification methods by de Carvalho and Freitas

Sentiment Analysis
Chapter on naive Bayes and sentiment classification from Jurafsky and Martin
Very extensive tutorial materials on sentiment analysis by Christopher Potts including detailed instructions about using word lexicons.
Survey papers on opinion mining and sentiment analysis: by Pang and Lee (2008) and by Liu and Zhang (2012)

Sequential Classifiers
Chapter on recurrent and recursive neural networks from Goodfellow et al (2016)

Document Clustering
Chapters on flat clustering algorithms and hierarchical clustering algorithms for text documents, from Manning et al

Topic Modeling
Tutorial paper on topic modeling by Steyvers and Griffiths
David Blei's page on topic modeling

Vector Embeddings
Chapter on dense vector representations for words from Jurafsky and Martin
Chapter on latent semantic indexing from Manning et al

Information Extraction
Chapter on information extraction from Jurafsky and Martin
Paper on extracting information about aspects of product from reviews by Zha et al (2014)

Text Summarization
Survey of text summarization techniques by Nenkova and McKeown (2012)

Natural Language Generation, Text Synthesis
Wikipedia resources related to natural language generation

Question Answering
Chapter on techniques for question-answering systems from Jurafsky and Martin
Paper on toy tasks for developing question-answering systems by Weston et al (2016)