The syllabus consists of
Slides
Weekly exercises
Mandatory assignments
Mandatory readings:
Jurafsky and Martin, Speech and Language Processing, 3. ed. (edition of 16 Oct,. 2019!)
- Ch. 2 Regular expressions etc
- Sec. 2.0
- Sec. 2.2-2.5
- except 2.4.3 and the technical details of 2.4.1
- Ch. 3, "N-gram Language Models"
- Sec. 3.0-3.4
- Ch. 4, "Naive Bayes Classification and Sentiment"
- Everything except section 4.9 Statistical significance testing
- Ch. 5, "Logistic Regression"
- Except the technicalities of sections 5.3, 5.4, 5.5, 5.8
- Ch. 6, "Word Semantics and Embeddings"
- Everything except sec. 6.7 Optional: PMI
- Ch. 7, "Neural Networks and Neural Language Models"
- Ch. 8 Part-of-speech-tagging,
- Everything except Viterbi algorithm, sec. 8.4.5, 8.4.6 and partly 8.4.7 and 8.4.8
- Ch. 9, "Sequence Processing with recurrent Networks"
- Sec. 9.0-9.2
- Ch. 10 "Encoder-decoder models"
- Sec. 10.0-10.2
- Ch. 17, "Information extraction"
- Sec. 17.1, "Named Entity Recognition"
- Sec. 17.2, "Relation Extraction"
- Ch. 26, "Dialogue systems and chatbots"
- Ch. 27, "Phonetics"
- Sections 27.1-27.5
- Ch. 3, sec. 6 Normalizing Text
- Ch. 3, sec. 8 Segmentation
- Ch. 5, sec. 1 Using a tagger
- Ch. 5, sec. 2 Tagged corpora
Wikipedia
Other
- Garrod, S., & Pickering, M. J. (2007). Alignment in dialogue. The Oxford handbook of psycholinguistics, 443-451.
- Section 24.6 of 2nd edition of Jurafsky & Martin (on MDPs).
- Mandatory readings on ethics at Week 11 page