Teaching

CS 4705: Introduction to Natural Language Processing, Fall 2007

Time: Tues/Thurs 2:40-3:55
Place: 327 Mudd

Professor Julia Hirschberg (Office Hours Tues 4:00-5:00, Wed 10:00-11:00)
julia@cs.columbia.edu, 212-939-7114

Teaching Assistant Frank Enos (Office Hours Tues/Thurs 1:00-2:00)
frank@cs.columbia.edu, 212-939-7193

Announcements | Academic Integrity | Contributions | Description
Links to Resources | Requirements | Syllabus | Text

Announcements:

  1. Check Columbia Courseworks for announcements, your grades (only you will see them), and discussion. Professor Hirschberg and your TA will monitor the discussion lists to answer questions.
  2. If you are interested in doing NLP research projects for credit, please let Professor Hirschberg know. The NLP group often has research opportunities available.  Other postings may be found at this location.

Description:

This course provides an introduction to the field of computational linguistics, aka natural language processing (NLP). We will learn how to create systems that can understand and produce language, for applications such as information extraction, machine translation, automatic summarization, question-answering, and interactive dialogue systems. The course will cover linguistic (knowledge-based) and statistical approaches to language processing in the three major subfields of NLP: syntax (language structures), semantics (language meaning), and pragmatics/discourse (the interpretation of language in context). Homework assignments will reflect research problems computational linguists currently work on, including analyzing and extracting information from large online corpora.

Textbook:

Speech and Language Processing by Jurafsky and Martin. It will be available from the University Bookstore, as well as from Amazon and other online providers. It should also be on reserve in the Engineering Library. Please check the online errata for the text for each chapter as you read it. 

Requirements:

Four homework assignments, a midterm and a final exam. Each student in the course is allowed a total of 4 late days on homeworks with no questions asked; after that, 10% per late day will be deducted from the homework grade, unless you have a note from your doctor.  Do not use these up early!  Save them for real emergencies. 

All students are required to have a Computer Science Account for this class. To sign up for one, go to the CRF website and then click on "Apply for an Account".

Homework submission procedure.

Academic Integrity:

Copying or paraphrasing someone's work (code included), or permitting your own work to be copied or paraphrased, even if only in part, is not allowed, and will result in an automatic grade of 0 for the entire assignment or exam in which the copying or paraphrasing was done. Your grade should reflect your own work. If you believe you are going to have trouble completing an assignment, please talk to the instructor or TA in advance of the due date.

Syllabus

Topic Reading Assignments

Week 1
Sep 4 Introduction and Course Overview    
Sep 6 Natural Language and Formal Language: Regular Expressions and Finite State Automata Ch 1-2  

Week 2
Sep 11 Words and Their Parts:  Morphology Ch 3:1  
Sep 13 Word Construction and Analysis: Morphological Parsing Ch 3:2-6 HW1 assigned; text inputs file1 and file2

Week 3
Sep 18 Word Tokenization, Pronunciation and Spelling Ch 5:1-8  
Sep 20 N-grams and Language Models Ch 6  

Week 4
Sep 25 Word Classes and POS Tagging; Questions Ch 8 HW1 due
Sep 27 Machine Learning Approaches to NLP and Introduction to Weka Jansche & Abney02 HW2 assigned; FAQ

Week 5
Oct 2 Context-Free Grammars Ch 9 Guest Speaker:  Owen Rambow
Oct 4 Parsing with Context Free Grammars Ch 10  

Week 6
Oct 9 Probabilistic and Lexicalized Parsing Ch 12 (Be sure to replace figure 12.3 with new version )  
Oct 11 Catching Up; Representing Meaning Ch 14  

Week 7
Oct 16 Semantic Analysis and Midterm Review Ch  15:1,4-6  
Oct 18 Midterm Examination Sample midterm  

Week 8
Oct 23 Relations Among Words Ch 16:1-2  
Oct 25 WordsEye Ch 16:3-5 Guest Speaker: Robert Coyne

Week 9
Oct 30 Word Sense Disambiguation Ch 17:1-2  
Nov 1 Information Retrieval and Information Extraction Ch 17:3-5 HW2 due (2pm); how to submit

Week 10
Nov 6 Holiday Holiday Holiday
Nov 8 Pronouns and Reference Resolution Ch 18: 18.1 HW3 assigned

Week 11
Nov 13 Algorithms for Reference Resolution    
Nov 15 Text Coherence and Discourse Structure Ch 18.2-18.5; Grosz&Sidner86 Guest Speaker: Frank Enos

Week 12
Nov 20 Turn-taking and Grounding Ch 19:1 Guest Speaker: Agustín Gravano
Nov 22 Thanksgiving Holiday    

Week 13
Nov 27 Dialogue Systems Ch 19:2-6  
Nov 29 Summarization and Generation Ch 20 HW3 due

Week 14
Dec 4 Machine Translation Ch 21 Guest Speaker: Nizar Habash
Dec 6 Final Review    

Week 15
Dec 11-13     Study Days
Dec 14-21     Final Exams

Links to Resources

cf. also resources available from the text homepage

General

  1. Karen Chung Language and Linguistics links
  2. CatSpeak

Places to look up definitions and descriptions of terminology:

  1. Oxford Dictionary of Linguistics
  2. Interesting Language Factoids and Non

Chapters 1 and 2

Try out one of the many versions of Eliza on the web.

Chapter3

AT&T Labs - Research Finite State Machine Library

Later Chapters

  1. Appelt and Israel's information extraction tutorial (IJCAI-99).
  2. Framenet.

Chapter 19

  1. Ask Jeeves-- a search engine that answers questions in plain English.
  2. Answer Bus -- another Q/A system.
  3. Columbia's NewsBlastersummarizer
  4. IBM summarizer demo (canned)
  5. Systran machine translation (also in use at Babelfish)
  6. AT&T Labs - Research Finite State Machine Library
  7. Michael Collins' Parser
  8. On-line dictionaries in many languages.
  9. WordNet
  10. Framenet
  11. CoBuildDirect Corpus
  12. AT&T's SCANMail voicemail browsing/search system
  13. DiaLeague 2001 -- includes a link to an online dialogue system demo.
  14. James Allen's Dialogue Modeling for Spoken Language Systems ACL 1997 Tutorial
  15. Festival speech synthesizer demo and links to other TTS systems
  16. Julia Hirschberg's Intonational Variation in Spoken Dialogue Systems tutorial

Julia Hirshberg Portrait

Julia Hirschberg
Professor, Computer Science

Columbia University
Department of Computer Science
1214 Amsterdam Avenue
M/C 0401
450 CS Building
New York, NY 10027

email: julia@cs.columbia.edu
phone: (212) 939-7114

Download CV

Columbia University Department of Computer Science / Fu Foundation School of Engineering & Applied Science
450 Computer Science Building / 1214 Amsterdam Avenue, Mailcode: 0401 / New York, New York 10027-7003
Tel: 1.212.939.7000 / Fax: 1.212.666.0140