11-731: Machine Translation

Prerequisites:

• 11-721 "Grammars and Lexicons" or equivalent background is recommended.
• 11-711 "Algorithms for NLP" or equivalent background is recommended.

Course Description

Machine Translation is an introductory graduate-level course surveying history, techniques, and research topics in the field.

The main objectives of the course are:

• Obtain a basic understanding of MT systems and MT-related issues.
• Learn about theory and approaches in Machine Translation.
• Learn about basic techniques for MT development, in preparation for the MT Lab course and real-world MT system project development.
• Obtain in-depth knowledge of one current topic in MT, or
  Perform an analysis of a given MT problem, matching it with the most suitable techniques (includes research, report and presentation).

Detailed Class Webpage

Course Topics

1. Introduction to MT
2. History of MT
3. Modern Theory and Approaches for MT
   • Transfer Methods
   • Interlingua MT
   • Example-based MT
   • Statistical MT
   • Multi-Engine MT
4. MT System Development
   • Domain Analysis and System Spec.
   • Analyzer SW Development
   • Generator SW Development
   • Linguistic Knowledge Development
5. Issues and Other Topics in MT
   • Ambiguity & Ambiguity Resolution
   • Controlled Language Input/Output
   • Speech-to-Speech Translation
   • MT Workflow and Human Factors
   • MT Evaluation
   • What is a useful MT system?
   • Commercial MT Systems
   • Future of MT
6. Term Project Presentation & Discussion

Reading Materials

Recommended Reading:

W. John Hutchins and Harold L. Somers, "An Introduction to Machine Translation",
Academic Press, San Diego, 1992.

Arturo Trujillo, "Translation Engines: Techniques for Machine Translation"
Springer-Verlag Series on Applied Computing, 1999.

Grading Criteria

Students will be graded based on their performance on the following tasks:

• Homework: 2-3 assignments on lecture material
• Exams: In-class, close book
• Term Project: Class presentation, written paper
• Class Participation

EMail questions to teruko@cs.cmu.edu