Course Syllabus for
CS 388: Natural Language Processing
Chapter numbers refer to the text:
SPEECH and LANGUAGE PROCESSING
Chapter 1. NLP tasks in syntax,
semantics, and pragmatics. Applications such as information extraction,
question answering, and machine translation. The problem of ambiguity. The
role of machine learning. Brief history of the field.
- N-gram Language Models
Chapter 4. The role of language models. Simple N-gram models.
Estimating parameters and smoothing. Evaluating language models.
- Part Of Speech Tagging and Sequence Labeling
Lexical syntax. Hidden Markov Models (Forward and Viterbi algorithms and EM training).
- Basic Neural Networks
Any basic introduction to perceptron and backpropagation such as section 18.7 in
Artificial Intelligence: A Modern Approach (3rd ed),
Chapter 4 of
Machine Learning, or sections 5.0 - 5.3.3
of Pattern Recognition and Machine Learning.
- LSTM Recurrent Neural Networks
"Understanding LSTM Networks" blog post, optionally the original paper
- Syntactic parsing
Chapters 12-14. Grammar formalisms and treebanks. Efficient parsing for
context-free grammars (CFGs). Statistical parsing and probabilistic CFGs
(PCFGs). Lexicalized PCFGs. Neural shift-reduce dependency parsing (see
- Semantic Analysis
Chapters 18-20. Lexical semantics
and word-sense disambiguation. Compositional semantics. Semantic Role Labeling
and Semantic Parsing.
- Information Extraction (IE)
Chapter 22. Named entity
recognition and relation extraction. IE using sequence labeling.
- Machine Translation (MT)
Basic issues in MT. Statistical translation, word alignment, phrase-based
translation, and synchronous grammars.