|
Computational Linguistics Syllabus |
|
Course Outline |
|
Linguistics 581 |
|
Day |
Reading |
Assignment |
Lecture |
Background |
Code |
| Tue Jan 22 | Chapter 1 and Section 2.1 of Chapter 2. Jurafsky and Martin (J&M) History of Computational Linguistics. Regular Expressions and Unix demo. | Assignment 1. | Some history. Textbook intro | What is Computational Linguistics? | |
| Tue Jan 29 | Chapter 2, 2.1-2.4 Class held in Comp Ling Lab (in Social Science Research Lab in Professional Studies and Fine Arts) Finite-state automata. | Assignment: Lab exercises. | Textbook Ch. 2 slides | Remote login to lab Python Wiki Lab exercises | |
| Tue Feb 05 | Reading: Google's Python intro, Alan Gauld's Tutorial for nonprogrammers, Tutorial (non-programmers) Tutorial (programmers) Many other python links Sections 3.1-3.3 of Chapter 3. Introducing words and word parts. Sections 3.4-3.9 of Chapter 3. | Recognizer assignment. | Python intro Morphology and FSAs Introduction to transducers Textbook Ch. 3 slides | ||
| Tue Feb 12 | Section 3.10 of Chapter 3. Spelling Correction. Introduction to Viterbi algorithm. Chapter 4: J&M. 4.1-4.3. Word counting, frequency dictionaries, simple ngram models, the training corpus | Selected exercises from Ch. 3 | Spelling correction Brief probability intro | ||
| Tue Feb 19 | Chapter 4: J&M (ctd) Ngrams. Section 4.8 of Chapter 4: Introduction to NLTK language modeling tools. | Ngram assignment | Lecture, Entropy and Cross-Entropy. Entropy as expected information value; cross-entropy as an evaluation tool (pdf, ps) | ||
| Tue Feb 26 | Section 4.1-4.5 of chapter 4. Practicalities. Sections 4.5.3 Chapter 4. Sections 4.4 and 4.5.1, 4.5.2 Chapter 4. Smoothing, Add-1 smoothing, Kneser-Ney smoothing. Unknown words. | Tagging Assignment. | Lecture. Smoothing Lecture. Kneser-Ney Lecture. | aligner-0.2:Code stub for aligner assignment | |
| Tue Mar 05 | 5.1-5.4. Word-class and part of speech tagging. Rule-based taggers. | HMM Tagging problem. Unsmoothed log prob model for train.tag Viterbi decoding. The model that was coded in class, Probability model assignment |
Lecture. | ||
| Tue Mar 12 | 5.5. HMM Taggers | Max entropy assignment | Lecture:: BBoard slides (Slp05.pdf) | ||
| Tue Mar 19 | 6.6 Max ent models. Background. Linear regression and logistic regression. 6.7-6.8 Max Ent tagging and Max Ent Markov Models. Chapter 2 of the NLTK book. Corpora. Real experiements with real data. Taggers used on data. Evaluation. | NLTK Assignment One | Lecture | ||
| Tue Mar 26 | Chapter 12. Context Free Grammars of English, Treebanks | Grammar assignment Parsing assignment | topdown lecture Lecture: Top down parsing. Parsing as search. | td_parser-0.1:an implementation of a recursive descent top down recognizer. | |
| Tue Apr 02 | H'day | H'day | H'day | H'day | H'day |
| Tue Apr 09 | Chapter 13.1 Parsing. 13.4.1.2 CKY algorithm (bottum up parsing with a chart), Earley algorithm (top down parsing with chart) | Assigment: Midterm, Parser writing help | |||
| Tue Apr 16 | Chapter 14. Probabilistic Context Free Grammars | Assignment: Prob parsing assignment, CKy implementation in these notes | Lecture | ||
| Tue Apr 23 | Chapter 19. Lexical Semantics. Chapter 20. Computational Lexical Semantics. | Assignment: Lexical semantics assignment | |||
| Tue Apr 30 | Chapter 20. Computational Lexical Semantics. | Assignment: Comp ling final |