Instructor Mitch Marcus   Office: Levine 503  mitch (AT) cis.upenn.edu  Office Hours: TBA

Teaching Assistant Lucas Champollion Office: Williams 401/402 champoll (AT) ling.upenn.edu Office Hours: Tuesdays, 11am-12noon.

Teaching Assistant Qiuye Zhao Office: GRW 571 qiuye (AT) seas.upenn.edu Office Hours: Mondays, 3pm-4pm

Class Schedule: Tuesday & Thursday, 4:30pm to 6:00pm, Towne 307

Course Administrator: Cheryl Hickey, 502 Levine, 215-898-3538, cherylh (AT) cis.upenn.edu

Web Page: http://www.seas.upenn.edu/~cis530/

Textbooks:

Jurafsky & Martin, SPEECH and LANGUAGE PROCESSING: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition, Draft of 2nd edition (selections available in Ikon Copy Center, Levine Hall).

Chris Manning & Hinrich Shutze, Foundations of Statistical Natural Language Processing, MIT Press, 1999. (available online from the Penn campus)

Various supplementary readings.

Homework:

Homework will be distributed on the lectures and posted on the web page.

Late homeworks will be penalized.

Back to Top

CLASS MODULES

Links to classroom slides will appear below.

Lecture Notes are in Microsoft PowerPoint format. You can view them with either Microsoft PowerPoint or the free Microsoft PowerPoint Viewer.

Module 1: Introduction & Word-Based Methods  

• Course Introduction
• [ Slides: Introduction and Syllabus ]
  
• [ Slides: NLP Applications: A Quick Tour ]
  
• Introduction to Python [ Slides]
  
• Introduction to Information Theory [ Slides]
  
• N-Gram Word-Based Models of Syntax [ Slides]
  
  • Word Distributions
  • Smoothing & Backoff
• Word Classes and Part of Speech Tagging [ Slides I, ] [ Slides II ] [ Slides III ]
  
  • Tag Set Design
  • Hidden Markov Models
  • Transformation-based Learning
• Speech Recognition [ Slides ]
  • Why is Speech Recognition hard?
  • HMMs for speech

Module 2: Parsing

• Introduction to Syntactic Analysis
  
• Context Free Models for English Syntax [ Slides ]
  
• Basic CF Parsing Algorithms [ Slides ]
• Statistical Parsing of CFGs
  
  • Probabilistic CFGs [ Slides ]
  • Generative Statistical Models [ Slides ]
  • Discriminative Models for Parsing
• Enriched Models for NL Syntax
  
  • The inadequacy of CF Models
  • Feature Structures and Unification [ Slides ]
  • Tree Adjoining Grammars [ Slides ]

Module 3: Meaning

• Lexical Semantics [ Slides ]
  
  • Word Sense Disambiguation: Decision Lists, SVMs
• Logical Form and Semantics [ Slides ]
  
  • Introduction to Logical Form
  • Mapping from Syntactic Structures to LF
• Practical Methods: Information Extraction and Named Entity Recognition [ Slides ]
• Practical Methods: Naive Bayes for Spam Filtering; SVMS, Perceptrons Recognition [ Slides ]
• Discourse & Pragmatics
  
  • Text Coherence & Discourse Structure

Module 4: Putting the Pieces Together

• Machine Translation [ Slides ]
  
  • Statistical Translation: The state of the art [ Slides ]
  
  ** We are now here (more or less) - 4/28/2008 **
• Generation & Summarization
  
  • Text Planning, Content Determination and Realization
  • Statistical Techniques for Summarization

Back to Top

HOMEWORK ASSIGNMENTS

How to submit:

• 1. connect to eniac.seas.upenn.edu
• 2. type the command ' turnin -c cis530 -p hwx filename'
• 3. If the system requires to choose the section, type 'ALL'

Assignment I

• Due: Tuesday, Feb. 12th, 2008.   Solution

Assignment II

• Due: Thursday, Feb. 21th, 2008.
• test_corpus: the pool of sentences
• This homework plays a lot with the module nltk.probability. Please read the documentation first. doc

Assignment III

• Due: Tuesday, Mar. 18th, 2008.   data

Back to Top

OTHER RESOURCES

Python Resources

• http://www.python.org/
  
• http://www.rexx.com/~dkuhlman/python_101/python_101.html
  
• http://www.rexx.com/~dkuhlman/python_201/python_201.html
• http://www.awaretek.com/tutorials.html
• Downloadable versions of the book "Dive into Python"
• You can access O'Reily's Safari website, which has books such as Learning Python, Programming Python, Python in a Nutshell, and Python Cookbook, from the Penn library e-resources page. (Type "python" in the search box when you finally get to the Safari page.)
• Courtesy of Liang Huang, you can find excellent links to textbooks, online tutorials, etc. on the Python language on his CSE399 webpage, http://www.cis.upenn.edu/~lhuang3/cse399-python/resources.html.

Back to Top

---

For more information, please contact mitch (AT) cis.upenn.edu

Back to the CIS homepage