NYUAD CS-AD 220 – Spring 2017

Natural Language Processing

Syllabus 

http://bit.ly/2j1wucw


  • Class Hours: Tue/Thu 2:40 - 3:55
  • Class Location: C2-E048
  • Office Hours: By appointment

Slides and Handouts

All slides and handouts will be available online HERE.


Description

The field of natural language processing (NLP), also known as computational linguistics, is interested in the modeling and processing of human (i.e., natural) languages. This course covers foundational NLP concepts and ideas, such as finite state methods, n-gram modeling, hidden Markov models, part-of-speech tagging, context free grammars, syntactic parsing and semantic representations. The course will survey a range of NLP applications such as information retrieval, summarization and machine translation. Concepts taught in class will be reinforced in practice by hands-on assignments. 


Text Books

J+M: Daniel Jurafsky and James H. Martin. "Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition." (2nd Edition). Pearson Prentice Hall, 2008.  The book is available at the bookstore.

NH: Nizar Habash. "Introduction to Arabic Natural Language Processing." Synthesis Lectures on Human Language Technologies. Morgan & Claypool Publishers, 2010.  This book is available online (click HERE or HERE).


Requirements

Components of the Final Grade: There will be four homework assignments and two exams (one mid-term and one final).  The assignments are varied in form including on-paper exercises (such as walking through algorithms), hands-on programming, building systems using off-the-shelf tools, and data analysis. Assignments count for 55% (one earns 10% and three earn 15% each); exams count for 40% (20% midterm and 20% final); and class participation (asking questions and participating in discussions that demonstrate having read the assigned readings) earns 5%. 

Participation and Attendance Policies: Attendance is required. Every unexcused absence (i.e., not pre-cleared with instructor, or not with medical documentation provided to instructor) will automatically cause one grade level drop.  Participation is expected in class discussions of specific NLP problems and solutions in a way that demonstrates preparedness.

Assignment Submission Policies:  All assignments are due at 11:59pm on the due date specified in syllabus.  For late submissions, 10% will be deducted from the homework grade per each late day.


Academic Integrity

As set forth in NYU Abu Dhabi's Academic Integrity Policy, the relationship between students and faculty at NYU Abu Dhabi is defined by a shared commitment to academic excellence and is grounded in an expectation of fairness, honesty, and respect, which are essential to maintaining the integrity of the community. Every student who enrolls and everyone who accepts an appointment as a member of the faculty or staff at NYU Abu Dhabi agrees to abide by the expectation of academic honesty. The full policies and procedures relating to Academic Integrity may be found on the NYUAD Student Portal


Class Schedule

DateTopicReadingOther
1Tue Jan 24Introduction to NLPNone
2Thu Jan 26Introduction to NLPJ+M Chap 1
3Tue Jan 31Regular Expressions and Basic Text ProcessingJ+M Chap 2 (intro,2.1)Assignment 1: due by Session 7 (Feb 14 midnight)
4Thu Feb 2Regular Expressions and Basic Text ProcessingHandout
5Tue Feb 7Finite State AutomataJ+M Chap 2 (2.2)
6Thu Feb 9Finite State AutomataJ+M Chap 2 (2.3 to end) + Chap 3 (intro up to 3.2)
7Tue Feb 14Morphology and Finite State Transducers J+M Chap 3 (3.2 up to 3.8); Assignment 2: due by Session 13 (Mar 7 midnight)
8Thu Feb 16Morphology and Finite State Transducers J+M Chap 3 (3.8 to end); NH Chap 4 (intro and 4.1 only)
9Tue Feb 21Language ModelingJ+M Chap 4 (intro up to 4.5)
10Thu Feb 23Language ModelingJ+M Chap 4 (4.5 up to 4.9)
11Tue Feb 28Part-of-Speech TaggingJ+M Chap 5 (intro up to 5.5)
12Thu Mar 2Part-of-Speech TaggingJ+M Chap 5 (5.5 up to 5.8)
13Tue Mar 7Part-of-Speech Tagging /
Syntax and Parsing
J+M Chap 5 (5.8 to end); handout (Pasha et al., 2014)
14Thu Mar 9Syntax and ParsingJ+M Chap 12
SPRING BREAK - March 15 to March 25 March 14 is off also
15Tue Mar 28Syntax and ParsingnoneAssignment 3: due by Session 20 (Apr 13 midnight)
16Thu Mar 30Syntax and Parsing / Mid term Review
J+M Chap 13
17Tue Apr 4MIDTERMChapters 1, 2, 3, 4, 5
18Thu Apr 6Invited Talk - Professor ToussaintTBD
19Tue Apr 11Machine TranslationJ+M Chap 25 (intro up to 25.5)
20Thu Apr 13Machine TranslationHandout (Papineni et al., 2002)
21Tue Apr 18Machine TranslationJ+M Chap 25 (25.5 to end);Assignment 4: due by Session 27 (May 9)
22Thu Apr 20Machine TranslationHandout (Zens et al., 2002)
23Tue Apr 25Machine TranslationNH Chap 8
24Thu Apr 27Machine TranslationHandout (Habash+Sadat, 2006)
25Tue May 2Lexical SemanticsJ+M Chap 19
26Thu May 4Lexical SemanticsJ+M Chap 20
27Tue May 9Question Answering and SummarizationJ+M Chap 23
28Thu May 11Question Answering and Summarization / Review for Finalnone

Final: Monday May 15, 2017 @1:00pm-4:00pm -- Room CR-002