Dalhousie University    [  http://web.cs.dal.ca/~vlado/csci6509/coursecalendar.html  ]
Winter 2015 (Jan5-Apr10)
Faculty of Computer Science
Dalhousie University

CSCI 4152/6509 - Course Calendar (tentative)

[ Home | Calendar | Project | Misc | A0 | A1 | A2 | A3 | A4 | A5 | A6 | A7 | A8 | Login ]
#DateTitle 
  Part I: Introduction
1 Mon Jan  5Course Introduction
Course information: logistics and administrivia, textbook and other main references, evaluation scheme, academic integrity policy, tentative course schedule. Introduction to NLP (reading Ch.1 [JM]): natural language and other languages; NLP applications, NLP as a research area, NLP Research links and NLP Anthology http://aclweb.org/anthology-new/. Handout: Course syllabus
Files: Slides (PDF), Lecture notes (PDF). Reading: [JM] Ch.1
 
2 Wed Jan  7Introduction to Natural Language Processing
Short history of NLP. Levels of NLP.
Files: Slides (PDF), Lecture notes (PDF).
A0 out
3 Fri Jan  9About Course Project
Some reasons why NLP is hard, ambiguities at different levels of NLP, examples of lexical and syntactic ambiguities. Ambiguities at different levels of NLP (continued): syntactic, semantic, pragmatic levels; NLP metholodology; about course project: deliverables, P0, P1, P, R.
Files: Slides (PDF), Lecture notes (PDF).
 
  Part II: Stream-based Text Processing
4 Mon Jan 12 Introduction to Perl
About course project (continued): project types, choosing topic, resources; themes and previous topics. Part II: Stream-based Text Processing; Introduction to Perl, main Perl language features, strengths and weaknesses, resources, file names, running program, simple arithmetic, syntactic elements.
Files: Slides (PDF), Lecture notes (PDF).
 
5 Wed Jan 14Regular Expressions
Introduction to Perl (continued): reading input, declaring variables, counting lines. Regular expressions: reading: Section 2.1 [JM], simple example, use in Perl, examples.
Files: Slides (PDF), Lecture notes (PDF). Reading: Section 2.1 [JM]
A0 due
L1 Wed Jan 14Lab 1: SVN Tutorial Files: Slides (PDF), Lab notes (PDF). 
6 Fri Jan 16Elements of Morphology
Perl Examples: counting and extracting letters, words and sentences; Elements of Morphology: reading: Section 3.1 [JM]; morphemes, stems, affixes, tokenization, stemming, lemmatization; morphological processes.
Files: Slides(PDF), Lecture notes (PDF). Reading: Section 3.1 [JM]
 
7 Mon Jan 19Characters, Words, and N-grams
Morphological processes (continued): inflection, derivation, compounding; Characters, Words, and N-grams: Zipf's law, counting n-grams.
Files: Slides (PDF), Lecture notes (PDF).
 
8 Wed Jan 21N-grams
Counting n-grams, scalar vs. array context in Perl, subroutines in Perl; Using Ngrams module.
Files: Slides (PDF), Lecture notes (PDF).
 
L2 Wed Jan 21 Lab 2: Perl Tutorial 1 Files: Slides (PDF), Lab notes (PDF).A1 due
  Part III: Similarity-based Text Processing
9 Fri Jan 23Elements of Information Retrieval
Elements of information retrieval, basic task definition of ad-hoc retrieval, typical IR system architecture, vector space model, IR evaluation measures; example with precision-recall curves, other evaluation measures.
Files: Slides (PDF), Lecture notes (PDF). Reading: [JM] 23.1 (Information Retrieval), [MS] Ch.15 (Topics in Information Retrieval).
 
10 Mon Jan 26Similarity-based Text Classification
Text classification: introduction, CNG method, evaluating text classification, evaluation methods for classification.
Files: Slides (PDF), Lecture notes (PDF).
 
  Part IV: Probabilistic Approach to NLP
11 Wed Jan 28Probabilistic Approach to NLP
Evaluation methods for classification (continued); text clustering task description; Probabilistic approach to NLP: logical vs. plausible reasoning, plausibe reasoning approaches, probability theory as a plausible reasoning approach, brief probability theory elements review; Bayesian inference: generative models.
Files: Slides (PDF), Lecture notes (PDF).
 
L3 Wed Jan 28Lab 3: Perl Tutorial 2 Files: Slides (PDF), Lab notes (PDF).A2 due
12 Fri Jan 30Probabilistic Modeling
Bayesian inference (continued); Probabilistic modeling: random variables, random models, full and partial model configurations, computational tasks in probabilistic modeling, joint distribution model, spam example.
Files: Slides (PDF), Lecture notes (PDF).
 
13 Mon Feb 2Naive Bayes Model
Drawback of joint distribution model. Fully independent model. Naive Bayes classification model: assumption, graphical representation, parameters, example, computational tasks.
Files: Slides (PDF), Lecture notes (PDF).
P0 due
14 Wed Feb 3N-grams Model
Naive Bayes model (continued). N-gram model: assumption, graphical representation, n-gram model as Markov chain, perplexity.
Files: Slides (PDF), Lecture notes (PDF). Reading: [JM] Ch 4
 
L4 Wed Feb 4Lab 4: Perl Tutorial 3 Files: Slides (PDF), Lab notes (PDF), Additional slides (PDF).A3 due
  Fri Feb 6Munro Day, University closed, no class  
15 Mon Feb 9Smoothing
Use of language modeling in classification. Smoothing: add-one, Witten-Bell discounting, example.
Files: Slides (PDF), Lecture notes (PDF).
 
16 Wed Feb 11P0 Projects discussion
Discussion about projects (not finished).
Files: Slides (PDF), Lecture notes (PDF).
 
  Thu Feb 12Assignment 4 due A4 due
17 Fri Feb 13POS Tags
Discussion about projects (finished). Parts-of-speech (POS), reading: [JM] Sec 5.1-5.3.
Files: Slides (PDF), Lecture notes (PDF). Reading: [JM] Sec 5.1-5.3. (POS)
 
  Mon Feb 16Study break Mon-Sun, Feb 16-20  
18 Mon Feb 23Hidden Markov Model
POS (continued): adverbs, other classes, examples. Hidden Markov Model: definition, HMM assumption, applications, POS tagging using HMM, computational tasks.
Files: Slides (PDF), Lecture notes (PDF). Reading: [JM] Ch. 6 (HMM, first part)
 
19 Wed Feb 25Bayesian Networks
HMM POS Example: brute-force approach, dynamic programming approach, Viterbi algorithm; Bayesian Networks: definition, assumption, example, why is inference in BNs expensive.
Files: Slides (PDF), Lecture notes (PDF). Reading: Sec 5.5 (HMM POS tagging)
A5 due
20 Fri Feb 27Product-Sum Algorithms
Inference in Tree Bayesian Networks; Product-sum algorithms: factor graphs, message passing, solving computatinoal tasks, burglar-earthquake example.
Files: Slides (PDF), Lecture notes (PDF).
 
21 Mon Mar 2HMM Tagging with Product-Sum Algorithm
HMM as a Bayesian Network, tagging example using product-sum algorithm.
Files: Slides (PDF), Lecture notes (PDF).
P1 due
  Part V: Parsing (Syntactic Processing)
22 Wed Mar 4Syntax and Context-Free Grammars
Syntax: phrase structure, phrases, clauses, sentences; reading: [JM] Ch 12; parsing, parse tree examples. Context-Free Grammars (CFG) review, examples, bracket notation, some notes about CFG notation.
Files: Slides (PDF), Lecture notes (PDF). Reading: [JM] Ch 12
 
23 Fri Mar 6Phrase Structure Rules for English
Typical phrase structure rules in English: Sentence (S), Noun Phrase (NP), Verb Phrase (VP), Prepositional Phrase (PP), Adjective Phrase (ADJP), Adverbial Phrase (ADVP). Are NLs context-free? Natural Language Phenomena: agreement, movement, subcategorization; heads and dependency.
Files: Slides (PDF), Lecture notes (PDF).
A6 due
24 Mon Mar 9Parsing and CYK Algorithm
Head feature principle, dependency trees, arguments and adjuncts; Parsing natural languages, CYK algorithm.
Files: Slides (PDF), Lecture notes (PDF).
 
25 Wed Mar 11Probabilistic Context-Free Grammars
CYK algorithm (continued). Probabilistic Context-Free Grammar (PCFG); reading: [JM] Chapters 13 and 14 (PCFG); computational tasks for PCFG model: evaluation, learning, simulation, proper PCFG; efficient inference in the PCFG model: modified CYK algorithms.
Files: Slides (PDF), Lecture notes (PDF). Reading: [JM] Chapters 13 and 14 (PCFG)
A7 due
L5 Wed Mar 11Lab 5: Prolog Tutorial 1 Files: Slides (PDF), Lab notes (PDF). 
  Part IV: Semantics and Unification-based NLP
26 Fri Mar 13Semantics and Unification-based Approach to NLP
Issues with PCFGs, a solution approach: probabilistic lexicalized CFGs; parser evaluation: PARSEVAL measures. Semantics and Unification-based NLP: Elements of semantics; lexical semantics, semantic compositionality, semantic roles. Theoretical foundations of the unification-based approach: first-order predicate calculus, inference rules, resolution-based inference system
Files: Slides (PDF), Lecture notes (PDF). Reading: [JM] 17-17.2 (Representation of meaning), [JM] 18.6 (Idioms and Compositionality), [JM] 19-19.3 (Lexical Semantics and WordNet), [JM] 14.7 (page 479, Evaluating parsers), [JM] 17.3 (First-order Predicate Logic).
 
27 Mon Mar 16DCG -- Definite Clause Grammars
Prolog overview: relation to resolution inference and Horn clauses, unification and backtracking, elements; using difference lists to parse NL; Definite Clause Grammars (DCG), examples: basic, with a parse tree, handling agreement, PCFG.
Files: Slides (PDF), Lecture notes (PDF).
 
  Wed Mar 18University Closed -- Snow Day  
  Wed Mar 18(Lab) University Closed -- Snow Day  
  Thu Mar 19A8 due A8 due
28 Fri Mar 20 Classical Unification
Classical unification: examples; substitution, unifier, composition of substitutions, most general unifier.
Files: Slides (PDF), Lecture notes (PDF).
 
29 Mon Mar 23 Feature Structures
Unification algorithms, Robinson's algorithm, running time; unification using graph representation, Huet's unification algorithm, example; Unification-based grammars using feature structures; reading: [JM] Chapter 15 (Features and Unification); feature structures or attribute-value matrices, DCG expressed using AVMs, lists in AVMs, graph representation of feature structures, re-entrancy in AVMs, cyclic AVMs, PATR-II notation style; feature structure unification, example.
Files: Slides (PDF), Lecture notes (PDF). Reading: [JM] Chapter 15 (Features and Unification)
 
30 Wed Mar 25Course Review 1 Files: Slides (PDF), Lecture notes (PDF). 
L6 Wed Mar 18 Lab 6: Prolog Tutorial 2 Files: Slides (PDF), Lab notes (PDF). 
31 Fri Mar 27 Course Review 2 Files: Slides (PDF), Lecture notes (PDF). 
  Part VII: Student Presentations
32 Mon Mar 30Student presentations (PT-24*, PT-25*, PT-26*, PT-27*)
PT-24: Dijana Kosmajac. PT-25: Hassan Nikoo. PT-26: Jordan Stirling. PT-27: Yajing Wu.
 
33 Wed Apr 1Student presentations (PT-20*, PT-21*, PT-22*, PT-23*)
PT-20: Ian Graven. PT-21: Webber Wang. PT-22: Baifan Hu. PT-23: Qingxue Xu.
 
34 Wed Apr 1(LAB) Student presentations (PT-16*, PT-17*, PT-18*, PT-19*)
PT-16: Ramkumar Velmurugan. PT-17: Walter Adbe: Spam Detection in Web Pages using Different Approaches in NLP. PT-18: Mathew Kallada. PT-19: Tyler Brunet.
 
  Fri Apr  3Good Friday, University closed, no class  
35 Mon Apr 6Student presentations (PT-12*, PT-13*, PT-14*, PT-15*)
PT-12: Hemangi Patel: Opinion mining and semantic analysis. PT-13: Mahsa Forati. PT-14: Andrey Kulakevich and Tyler Pachal. PT-15: Craig McInnis.
 
36 Wed Apr 8 Student presentations (PT-08*, PT-09*, PT-10*, PT-11*)
PT-08: Utsav Patel. PT-09: Nisha Simon. PT-10: Hardik Dalal. PT-11: Chahna Dixit.
 
37 Wed Apr 8 Student presentations (Lab) (PT-04*, PT-05*, PT-06*, PT-07*)
PT-04: He Huang and Yiying Zhang. PT-05: Ke Zhang. PT-06: Yiming Li. PT-07: Yun Wan.
 
38 Fri Apr 10 Student presentations, Course Evaluation (PT-01*, PT-02*, PT-03*)
PT-01: Alex Safatli. PT-02: Wei Wei. PT-03: Kai Qi.
Report due
  Thu Apr 16Final Exam (12:00-14:00)
Final exam, duration 2 hours, starting at 12:00, location Dunn 101. Exam schedule URL: http://www.dal.ca/academics/exam_schedule/halifax_campus_exam_schedule.html
Exam

© 2002-2015 Vlado Keselj, last update: 25-Mar-2015