CS 6890
Natural Language Processing

Course Description

Research introduction to several fundamental topics in the field of natural language processing. Topics include, but are not limited to:

• Language and Complexity;
• Morphology and Finite-State Transducers;
• N-Grams;
• Parsing with Context-Free Grammars;
• Speech Synthesis;
• Language Generation;
• Information Extraction.

Objectives

• To familiarize students with the Chomsky Hierarchy and its use in estimating the complexity of various languages;
• To familiarize students with foundations of morphology and the use of finite state transducers for morphological processing;
• To familiarize students with N-grams and their use in probabilistic language processing;
• To introduce students to the top-down and bottom-up parsing and the Early algorithm;
• To introduce students with basic notions of phonology and their use in speech synthesis;
• To introduce students to the Festival speech synthesis system and enable students to use the system in a limited domain project;
• To familiarize students with basic notions of language generation;
• To familiarize students with basic notions of information extraction.

Text Books

There are no required textbooks for this class. Students will read research papers, articles, and selected chapters from various textbooks.

Assignments

There will be regular reading assignments throughout the semester. There will also be several programming assignments. There will also be several in-class presentations.

Please be cognizant of deadlines and due dates. Your grades will be periodically posted on the Eagle server. If you do not have an account on that server, go to the above link and follow the instructions on how to get a new account. You have to have a valid cc.usu.edu e-mail address before you can get an account on Eagle.

You must be registered for the class in order to submit your assignments, have them graded, and take exams. If you are not registered, the grader will not grade your homework submissions. If the grader grades your homework by mistake, you will receive no credit for your work.

Grading

• Homework - 20 percent;
• Presentations - 30 percent;
• Final project - 50 percent.

Plagiarism

You are free to talk with each other about regular assignments in general terms. However, you must write your own solutions and/or computer code. No collaboration is allowed on exams.

Activities that violate the plagiarism policy include (but are not limited to): copying another person's work on a programming project, homework assignment, or exam; using any reference not authorized by the instructor on a programming project, homework assignment, or exam.

The penalty for violating the plagiarism policy may be an F in the course. Appropriate university authorities may be informed of cheating incidents in a formal letter.

ADA Compliance

If a student has a disability that will likely require some accomodation by the instructor, the student must contact the instructor and document the disability through the Disability Resource Center, preferably during the first week of the course. Any request for special considerations relating to attendance, pedagogy, taking of examinations, etc. must be discussed with and approved by the instructor. In cooperation with the Disability Resource Center, course materials can be provided in alternative formats, e.g., large print, audio, diskette, or Braille.

Incompletes

The University policy will be adhered to for incompletes. This means that an incomplete cannot be given to prevent receipt of a bad grade. Under no circumstances can an incomplete be given for which a re-take of the class is required to make up the work. In such situations, a withdrawal or late withdrawal is required. If a student feels that an incomplete is appropriate, it is their responsibility to immediately discuss the matter with their instructor.

Contact

My office is in 401E, Old Main. My office hours for this class is 4:00pm to 5:00pm on Wednesday or by apppointment. My e-mail is vladimir.kulyukin@usu.edu.