Références

Littérature

M. Rajman editor, "Speech and Language Engineering", EPFL Press, 2007.
Daniel Jurafsky and James H, Martin, "Speech and Language Processing", Prentice Hall, 2008 (2nd edition)
Note: third edition is in preparation: see https://web.stanford.edu/~jurafsky/slp3/
Christopher D. Manning and Hinrich Schütze, "Foundations of Statistical Natural Language Processing", MIT Press, 2000
Christopher D. Manning, Prabhakar Raghavan and Hinrich Schütze, Introduction to Information Retrieval, Cambridge University Press. 2008
Jacob Eisenstein, "Introduction to Natural Language Processing", MIT Press, 2019
Nitin Indurkhya and Fred J. Damerau editors, "Handbook of Natural Language Processing", CRC Press, 2010 (2nd edition)
Robert Dale, Hermann Moisl, Harold Sommers editors, (an older) "Handbook of Natural Language Processing", Dekker, 2000
Eugene Charniak, "Statistical Language Learning", MIT Press, 1993
Emmanuel Roche and Yves Shabes (eds.), "Finite State Language Processing", MIT Press, 1997
Rabiner, L.R., and Huang, B.H., "Fundamentals of Speech Recognition", Prentice Hall, 1993

Relationship with the lectures

	[1]	[2]	[3]	[4]	[5]	[6]
Introduction	(1. Components of a NL Grammar)	1. Introduction	1. Introduction	—	1. Introduction	1. Classical Approaches to NLP
Evaluation	10.9	5.7, 9.8, 23.7 & 24.4.2	5.3 Hypothesis testing 8.1 Evaluation Measures	8. Evaluation in IR	4.4 Evaluating Classifiers 4.5 Building Datasets	—
Tokens, words and Language Models	—	todo	todo	todo	6.1 N-Gram Language Models Smoothing and Discounting	2.1-2.3 Text Preprocessing
PoS tagging	8.4 PoS Tagging & Lemmatization	5. PoS Tagging 6. HM & ME Models	3.1 PoS & Morphology 10. PoS Tagging 9. Markov Models	—	7. Sequence Labeling	10. PoS Tagging
HMM decoding and learning	todo	todo	todo	todo	7.3 The Viterbi Algorithm 7.4 Hidden Markov Models 8.1 Part-of-Speech Tagging 5.2 Applications of Expectation-Maximization	todo
Text Classification	—	—	14. Clustering 16. Text Categorization	13. Text classif. & Naive Bayes 14. VS classification 15. SVM & ML on documents 16. Flat clustering 17. Hierarchical clustering 18. Matrix decomposition & LSI	2. Linear Text Classification	—
Vector space Semantics (and Information Retrieval)	10.5 to 10.8	23.1 Information Retrieval	15. Topics in IR	6. Scoring, term weighting, ... 7. Computing scores... 8. Evaluation in IR	14.1 The Distributioal Hypothesis 14.2 Design Decisions for Word Representations	19. Information Retrieval
Lexical Semantics	10.11 Lexical Semantics in LE 10.14 Lex. Sem. Resources	19. Lexical Semantics 20. Computational Lex. Sem.	3.3 Semantics & Pragmatics	—	todo	Semantic Analysis: 5.1, 5.3
Neural Networks approaches to NLP (inc. Deep-Learning)	—	todo	todo	todo	3. Nonlinear Classification 6.3 Recurrent Neural Network Language Models 14.5 Neural Word Embeddings	todo
Generation	—	todo	todo	todo	19. Text Generation	todo
Modern NLP	—	todo	todo	todo	todo	todo