CS 224U / LING 188 / LING 288
Natural Language Understanding
Winter 2010

ANNOUNCEMENTS
COURSE INFORMATION
Staff
Instructor: Dan Jurafsky, jurafsky @ stanford.edu Office Hours: Tuesday 4:30-5:30, Thursday 2-2:30.
Instructor: Bill MacCartney,    wcmac @ cs.stanford.edu Office Hours: TBD
TA: Adam Vogel, cs224u-ta @ cs.stanford.edu Office Hours: Gates 114, Tuesday 12-1:30 (and by appointment)

All of us:    cs224u-win0910-staff @ lists.stanford.edu
Time
TuTh 3:15-4:30pm
Location
Cummings Art Room 4 (click for map)
Catalog Description
Machine understanding of human language. Computational semantics (determination of sense, event structure, thematic role, time, aspect, synonymy/meronymy, causation, compositional semantics, treatment of scopal operators), and computational pragmatics and discourse (coherence relations, anaphora resolution, information packaging, generation). Theoretical issues, online resources, and relevance to applications including question answering, summarization, and textual inference. Prerequisites: one of LINGUIST 180, CS 224N,S; and knowledge of logic (LINGUIST 130A or B, CS157, or PHIL159)
Requirements
  1. Read the papers before each class
  2. Do the 6 data homeworks. Each one of these will require a small amount of work to learn about a natural language understanding data source. You will be asked to answer small questions and make note of interesting points you notice about the data. Be creative! You can talk to friends about the data, but the actual data homeworks must be your own work. Here is the homework policy.
  3. Do the 1 programming homework. The programming homework is to be done by yourself, not in groups.
  4. Write a literature review paper: a short 6-page single-spaced paper summarizing and synthesizing 5 papers on the area of your final project. This may be done in groups (the same groups you use for your final project). The ideal is to have the same topic for your lit review and final project, but it's possible that you'll discover in the lit review that you hate the topic and so it's allowable to switch topics (or groups) for the final project, if you want.
  5. Do a final project: a research project due at the end of the quarter. Both the final project and the review paper may be done in groups. Paper formatting and etc details here
  6. Your grade is determined based on:
      Class participation: 10%
      Data HW assignments: 15%
      Programming HW assignments: 15%
      Literature review: 20%
      Final Project: 40%
    HW assignments are graded on a -/v/+ basis, where '-' is insufficient and '+' is exceptional.
    In accord with the usual practice at Stanford, the work of students registered for the undergrad version of the course (LING188) will be graded on an easier basis.
Updates

Homeworks require access to the linguistic data on AFS. Instructions to get access.




SCHEDULE
Wk
Date
HW Due
Who

Topic and Readings

1
 Jan 5
 Dan
Lec 1 (pptx)
Lec 1 (pdf)

History

  • Terry Winograd. 1972. Understanding Natural Language. Academic Press, New York. Sections 1-2.
  • Schank and Abelson. 1977. Scripts, Plans, Goals, and Understanding: An Inquiry into Human Knowledge Structures. Hillsdale, NJ: L. Erlbaum, . Chapters 1-3.

  • OPTIONAL ADVANCED READING:
    Robert F. Simmons. 1970. Natural language question-answering systems: 1969 Communications of the ACM 13:1, 15-30.
PART I: Lexical Semantics
1
 Jan 7
 Data HW 1 Dan
Lec 2 (pptx)
Lec 2 (pdf)

Lexical Relations: WordNet, Synonymy, Hyponymy

2
 Jan 12

Word Sense Disambiguation

2
 Jan 14
Data HW 2

Dan
Lec 4 (pptx)
Lec 4 (pdf)

Background on Parsing

  • Marie-Catherine de Marneffe, Bill MacCartney, and Christopher D. Manning. 2006. Generating Typed Dependency Parses from Phrase Structure Parses. 5th International Conference on Language Resources and Evaluation (LREC 2006), pp. 449-454.
  • [In addition, for those who haven't had parsing in CS 224N or the equivalent:] Jurafsky and Martin 2nd edition Chapter 13, Syntactic Parsing, pages 427-443
  • OPTIONAL READING:
    • Jurafsky and Martin 2nd edition Chapter 14, Statistical Parsing, pages 459-466
    • For those who haven't ever studied context-free grammar:
      Jurafsky and Martin 2nd edition Chapter 12, Formal Grammars of English, pages 385-408 and 414-416
3
 Jan 19
Dan
Lec 5 (pptx)
Lec 5 (pdf)

Semantic/Thematic Roles

3
 Jan 21
Data HW 3 Guest Lecturer Chris Potts
Lec 6 (pdf)

Sentiment Analysis

4
 Jan 26
Dan
Lec 7 (pptx)
Lec 7 (pdf)

Relation Extraction

4
 Jan 28
Data HW 4

Submit (email all 3 of us) list of 5 papers for lit review

Bill
Lec 8 (ppt)
Lec 8 (pdf)

Learning Relations from the Web

PART II: Discourse
5
 Feb 2
Data HW 5 Dan
Lec 9 (pptx)
Lec 9 (pdf)

Coherence

5
 Feb 4
Lit Review due
 Dan
Lec 10 (pptx)
Lec 10 (pdf)

Anaphora and Coreference

PART III: Computational Formal Semantics
6
 Feb 9
Prog HW 1
submission instructions		 Bill

Building Semantic Representations: Lambda calculus

  • Patrick Blackburn and Johan Bos. 2003. Computational Semantics. Theoria, 18, 27-45.
  • Christopher Manning. 2005. An Introduction to Formal Computational Semantics. MS, Stanford U.
  • More detailed coverage [Optional]: Patrick Blackburn and Johan Bos. 2005. Representation and Inference for Natural Language: A first course in computational semantics. Stanford, CA: CSLI Publications.
6
 Feb 11
Data HW 6
Patrick Pantel

Practical Language Acquisition
7
 Feb 16
Bill

Scope Ambiguity and Underspecified Representations

  • Christopher Manning. 2005. An Introduction to Formal Computational Semantics. MS, Stanford U.
  • Derrick Higgins and Jerrold M. Sadock (2003). A machine learning approach to modeling scope preferences. Computational Linguistics 29(1), 73-96.
  • OPTIONAL ADVANCED READING:
    Patrick Blackburn and Johan Bos. 2005. Representation and Inference for Natural Language: A First Course in Computational Semantics. Stanford, CA: CSLI Publications. Chapter 3.
  • OPTIONAL ADVANCED READING:
    Bob Carpenter. 1997. Type-Logical Semantics. Stanford, CA: CSLI Publications. Chapters 3 and 7.
7
 Feb 18
Adam

Grounded Language Acquisition

8
 Feb 23
Ron Kaplan


  • TBD
8
 Feb 25
Bill

Learning to Map to Logical Forms for First order inference

9
 Mar 2
Cleo Condoravdi

Textual Inference

  • Bobrow, Danny, Cleo Condoravdi, Richard Crouch, Ronald Kaplan, Lauri Karttunen, Tracy Holloway King, Valeria de Paiva, and Annie Zaenen. 2005. A Basic Logic for Textual Inference. In Proceedings of the AAAI Workshop on Inference for Textual Question Answering, Pittsburgh, PA.
  • MacCartney, Bill, Trond Grenager, Marie-Catherine de Marneffe, Daniel Cer, and Christopher D. Manning. 2006. Learning to recognize features of valid textual entailments. To appear in Proceedings of NAACL-2006.

9
 Mar 4
 Bill Paraphrase
PART IV: Projects
10
 Mar 9

Project Presentations

10
 Mar 11

Project Presentations


Mar 15

Final Project due noon