CSCI 544

Applied Natural Language Processing

University of Southern California

Spring 2014


Time:

Mondays and Wednesdays
2:00pm-3:20pm

Location:

MHP105

Instructor:

Dr. Zornitsa Kozareva

Teaching Assistant:

TBD

Guest Lecturers:

TBD

Class Questions:

Use Piazza to post class related questions and/or to start a discussion
https://piazza.com/class#spring2014/csci544

Goals:

This course covers both fundamental and cutting-edge research topics in Natural Language Processing (NLP) and delves into modern NLP applications including: information extraction, information retrieval, question answering systems like IBM's Watson, sentiment analysis.

Audience:

This graduate course is intended for:
  • students who want to understand state-of-the-art and current NLP research
  • students interested in tools for building NLP applications
  • students interested in applications of NLP like sentiment analysis, information extractors, search engines among others

Prerequisities:

Proficiency in programming, algorithms and data structures, basic knowledge of linear algebra and machine learning.

Related Courses

There is a sister course, Advanced Natural Language Processing, offered in the fall semester. You can take these two courses in either order.


Textbooks (optional reading)


Classes from Previous Years

Syllabi and materials from previous years. Since those pages are no longer maintained, there is no guarantee of completeness.


Coursework:

Students will experiment with existing NLP software toolkits and write their own programs. Students will work with real datasets and will build their own NLP Information Extraction, Text Classification and Sentiment Analysis systems. Grades will be based on:
  • Programming assignments (2 x 25%): the grade will depend on the performance of a system relative to the rest of the class and the technical report.
  • Research project (50%): the grade will depend on the project's substantiality, correctness, relevance to the course, as well as the clarity and depth of the project report, which should follow standard ACL guidelines. Building a demo system will be optional, but will count as bonus points.

Homework and Project Proposal Guidelines

Homework I
Homework II
Project Proposal


Syllabus

Date Instructor Lecture
January 13 Kozareva Introduction
January 15 Kozareva Named Entity Recognition, Decision Trees
January 20 MLK Holiday
January 22 Kozareva Named Entity Recognition, k-NN, Feature Selection
January 27 Kozareva Introduction to Weka
Homework 1 is out
January 29 Kozareva Name Discrimination, Clustering
February 3 Kozareva Latent Semantic Analysis
February 5 Kozareva Applications of Latent Semantic Analysis
February 10 Kozareva Principal Component Analysis
February 14 Kozareva Latent Dirichlet Allocation
Homework 2 is out
February 17 Kozareva POS Tagging
February 19 Kozareva Parsing
February 24 President's Day
February 26 Kozareva Semantic Class Induction
March 3 Kozareva Graph Algorithms for NLP
March 5 Kozareva Taxonomies
March 10 Kozareva Sentiment Analysis
March 13 Kozareva Regression for NLP
March 17 Spring Break
March 19 Spring Break
March 24 Kozareva Bullying Detection
March 26 Kozareva Event Extraction
March 31 Kozareva Paraphrase Acquisition
April 2 Kozareva Textual Entailment
April 7 Kozareva Summarization
April 9 Kozareva Information Retrieval
April 14 Kozareva Question Classification
April 16 Kozareva Unsupervised Learning for Structured Prediction
April 21 Class Presentations
April 23 Class Presentations
April 28 Class Presentations
April 30 Class Presentations

Statement for Students with Disabilities:

Any student requesting academic accommodations based on a disability is required to register with Disability Services and Programs (DSP) each semester. A letter of verification for approved accommodations can be obtained from DSP. Please be sure the letter is delivered to me (or to TA) as early in the semester as possible. DSP is located in STU 301 and is open 8:30 a.m.-5:00 p.m., Monday through Friday. The phone number for DSP is (213) 740-0776.

Statement on Academic Integrity:

USC seeks to maintain an optimal learning environment. General principles of academic honesty include the concept of respect for the intellectual property of others, the expectation that individual work will be submitted unless otherwise allowed by an instructor, and the obligations both to protect one's own academic work from misuse by others as well as to avoid using another's work as one's own. All students are expected to understand and abide by these principles. Scampus, the Student Guidebook, contains the Student Conduct Code in Section 11.00, while the recommended sanctions are located in Appendix A: http://www.usc.edu/dept/publications/SCAMPUS/gov/. Students will be referred to the Office of Student Judicial Affairs and Community Standards for further review, should there be any suspicion of academic dishonesty. The Review process can be found at: http://www.usc.edu/student-affairs/SJACS/.

Emergency Preparedness/Course Continuity in a Crisis:

In case of a declared emergency if travel to campus is not feasible, USC executive leadership will announce an electronic way for instructors to teach students in their residence halls or homes using a combination of Blackboard, teleconferencing, and other technologies.