Topics

Readings

There is no required textbook. All readings will be selected from books, journal articles and conference papers that are available online freely for UMD students.

• Recommended resources
  • Speech and Language Processing (3rd edition draft) by Dan Jurfasky and James H. Martin
  • Foundations of Statistical Natural Language Processing by Chris Manning and Hinrich Schuetze
  • Linguistics Fundamentals for NLP by Emily Bender
  • A Course in Machine Learning by Hal Daumé III

Topics

• Introduction to Classification and Learning in NLP

  • Text classification
  • Word Sense Disambiguation
  • Supervised learning: Naive Bayes, Perceptron, Logistic Regression
  • Unsupervised learning: Expectation Maximization

• Sequences

  • Language Models: n-grams, smoothing, neural models
  • Morphology, Finite State Machines
  • Part-of-speech tagging, Hidden Markov Models, Structured perceptron

• Trees

  • Syntax
  • Dependency parsing: graph-based, transition-based and imitation learning
  • Constituency parsing and Context-Free Grammars

• Meaning

  • Formal Semantics
  • Shallow Semantics
  • Lexical and Distributional Semantics
  • Discourse

• Applications

  • Social impact of natural language processing
  • Machine translation
  • Textual entailment/inference