Skip to main content
LING 4466 Multilingual Methods in NLP
Spring 2024
Wednesdays 3:30-6:00
New North GW03
Linguistics Department
Georgetown University

This is a project based course focusing on the design and implementation of systems that scale Natural Language Processing methods beyond English. The course will cover both multilingual and cross-lingual methods with an emphasis on zero-shot and few-shot approaches, as well as ‘silver’ dataset creation. Modules will include Cross-Lingual Information Extraction & Semantics, Cross-Language Information Retrieval, Multilingual Question Answering, Multilingual Structured Prediction, Multilingual Automatic Speech Recognition, as well as other non-English centric NLP methods. Students will be expected to work in small groups and pick from one of the modules to create a model based on state-of-the-art methods covered in the class. The course will be roughly two-thirds lecture based and one-third students presenting project updates periodically throughout the semester.

Instructor
Kenton Murray (kwm37@georgetown.edu)
Office hours
By Appointment
Wednesdays 2:30-3:30pm
Method of Instruction
The course will primarily be lecture and discussion based. Students will be expected to participate in active discussions of the course material. However, the majority of the instruction will be lectures and outside presentations. Students will be presenting project proposals, mid-point status updates, and final presentations.
Piazza
Decision during first class.
Readings
This is an upper-level graduate course. Readings will be provided by the instructor when necessary and may include technical reports, book chapter excerpts, journal and conference papers, etc. There is no required text book for the course.
Grading
Homework will be a range of coding exercises and short-form questions aimed at introducing students to the cutting-edge methods of multilingual natural language processing.
  • Four homework assignments (7.5% each)
  • Final project (50%)
  • Class Participation (20%)
Homework Schedule
There will be four homework assignments, tentative schedule:

All assignments are due at 11:59PM on the day they are due. Exceptions regarding tardiness will be considered on a case-by-case basis and must be submitted via e-mail 24 hours before the initial due date. Late submissions will be accepted using an exponential decay formula with a half-life of 1 week (604800 seconds).