Machine Learning in the context of natural language processing (NLP) is concerned with statistical techniques for identifying various aspects of text. Some text is used to learn a model that can then be applied to new text. Possible tasks that can be performed with machine learning techniques are for instance part of speech tagging, named entity recognition, parsing, sentiment analysis, topic detection, semantic role labeling etc.
The course introduces machine learning techniques along with applications to standard NLP tasks.
References:
- Steven Abney (2008) Semisupervised Learning for Computational Linguistics. Chapman & Hall/CRC (Computer science and data analysis series, edited by David Madigan et al.).
- Daniel Jurafsky and James H. Martin
(2009). Speech and Language Processing. An Introduction to
Natural Language Processing, Computational Linguistics, and
Speech Recognition. Prentice Hall Series in Articial Intelligence.
Pearson Education International. Second Edition.
See here for a draft of the 3rd edition. - Christopher D. Manning, Prabhakar Raghavan and Hinrich Schütze, Introduction to Information Retrieval, Cambridge University Press. 2008.