iclf10_schedule

Introduction to computational linguistics, Fall 2010: Schedule

Schedule as of “Last modified” date at bottom. Subject to change.

Assignments are due at the end of their due date (midnight).

Readings can be done either before or after class; they are chosen to support the material covered in class.

Week 1

Date Topic Materials Reading Assignments
Aug 25 Introduction


Aug 27 A demo of the Natural Language Toolkit Code for the demo: course archive, intro_py.zip
NLTK book ch. 1

Week 2

Date Topic Materials Reading Assignments
Aug 30 Working with text corpora Slides: course archive, corpora.pdf
NLTK book ch. 2
Sep 1 Python basics Worksheet: first steps in Python: course archive,intro_python.pdf How to Think Like a Computer Scientist, ch.1 and ch.2
Sep 3 Python lists Worksheet: Python lists: course archive, python_lists.pdf HTTLCS, ch. 9

Week 3

Date Topic Materials Reading Assignments
Sep 6 Labor day


Sep 8 Python loops Worksheet: conditions and repetition in Python: course archive,python_loops.pdf HTTLCS, ch. 4 and ch. 6
Sep 10 Practising Python functions Worksheet: practising Python: course archive, practising_python.pdf HTTLCS, ch. 3 and ch. 5

Week 4

Date Topic Materials Reading Assignments
Sep 13 Regular expressions Since we'll also access files, here is information on how to access files in Python: course archive, python_files.ppt J&M ch.2 first half HW 1 due
Sep 15 More regular expressions Overview: regular expressions in Python: course archive,regexp.pdf NLTK ch. 3.4, 3.5
Sep 17 Finite-state automata
J&M ch.2 second half

Week 5

Date Topic Materials Reading Assignments
Sep 20 Finite-state automata and regular expressions


Sep 22 Words and transducers
J&M ch. 3, pp. 45-68
Sep 24 Computational morphology


Week 6

Date Topic Materials Reading Assignments
Sep 27 Finishing up computational morphology. Then: Python dictionaries Worksheet: Python dictionaries: course archive, python_dictionaries.ppt

HW 2 due
Sep 29 Using Python dictionaries: counting words


Oct 1 Sample Python programs Worksheet: sorting lists in Python, two sample Python programs: course archive, python_sorting.ppt, sample_python_progs.zip

Week 7

Date Topic Materials Reading Assignments
Oct 4 Working with probabilities


Oct 6 Working with probabilities some more


Oct 8 Language models Sample Python program useful for homework 3: course archive, dict_of_lists.zip  J&M ch. 4, pp 83-97

Week 8

Date Topic Materials Reading Assignments
Oct 11 Part-of-speech tagging
J&M ch. 5 pp. 123-135, NLTK book ch. 5, sec. 5.1 and 5.2 HW 3 due
Oct 13 Review for the midterm


Oct 15 Part-of-speech tagging and finite-state automata
NLTK book ch. 5, sec 5.4Take-home midterm exam

Week 9

Date Topic Materials Reading Assignments
Oct 18 Hidden Markov Models
J&M ch. 5 pp. 139-144, NLTK book ch. 5 sec. 5.5
Oct 20 Part-of-speech tagging and Hidden Markov Models Python code for estimating HMM probabilities from the Brown corpus: course archive,hmm_estimate_probs.zip J&M ch. 5 pp. 144-149, ch. 6 pp. 173-179
Oct 22 Chunking
NLTK book ch. 7, sec. 7.2 and 7.3

Week 10

Date Topic Materials Reading Assignments
Oct 25 Context-free grammars
J&M ch.12, pp. 385-404 HW 4 due
Oct 27 Context-free grammars for fragments of English


Oct 29 The Chomsky hierarchy
J&M, ch. 16, pp 529-542

Week 11

Date Topic Materials Reading Assignments
Nov 1 Parsing: top-down and bottom-up NLTK book ch. 8, 8.3 and 8.4 up to and including “Shift-Reduce Parsing” J&M ch. 13, pp. 427-432
Nov 3 Chart parsing
J&M ch. 13 pp. 432-450
Nov 5 Statistical parsing
J&M ch. 14 pp. 459-463, 467

Week 12

Date Topic Materials Reading Assignments
Nov 8 Semantics overview Slides: course archive, semantics_overview.pdf
HW 5 due
Nov 10 Classification Slides: making features: course archive,wsd_features.pdf

Nov 12 Word sense disambiguation
J&M ch. 20 pp. 637-645

Week 13

Date Topic Materials Reading Assignments
Nov 15 WordNet Slides on WordNet: course archive,wordnet.pdf J&M ch. 19, pp. 611-619
Nov 17 Vector space models of word meaning Slides: vector space models for web search and word meaning. course archive,vs_ir.pdf J&M ch. 20, pp. 658-663
Nov 19 Distributional similarity Sample Python program: a very simple vector space program: course archive, vspace.zip J&M ch. 20, pp. 663-667

Week 14

Date Topic Materials Reading Assignments
Nov 22 Pattern-based approaches to learning semantics from text
J&M ch. 20, p. 667-670 HW 6 due
Nov 24 More on pattern-based approaches
J&M ch. 22, p. 725-727, 734-743
Nov 26 [Thanksgiving]


Week 15

Date Topic Materials Reading Assignments
Nov 29 Clustering
J&M ch. 20, p. 674-675
Dec 1 Machine translation Slides: machine translation. course archive, mt.pdf J&M ch. 25, p. 859-876
Dec 3 Review Review sheet: course archive,final_review.pdf

Final exam

Wednesday, December 8, 2:00-5:00 pm

ċ
icl_fall10.zip
(3748k)
Katrin Erk,
Jan 6, 2012, 9:26 AM
Comments