LING 575 E: Topics In Computational Linguistics

Meeting Time: 
M 3:30pm - 5:50pm
Location: 
SAV 130
SLN: 
16280
Joint Sections: 
LING 575 F, LING 575 D
Instructor: 
Jeremy Gillmor Kahn

Syllabus Description:

LING 575: Care and feeding of neural networks for NLP

(subtitle: How to Train Your Dragon)

Instructor:  Jeremy Kahn

jgk@uw.edu

Mondays, 330-550p

27 March-29 May 2017 (inclusive).

First day of instruction: March 27

This course offers an introductory exploration of neural networks for natural language processing.  Neural networks are enjoying recent extraordinary success in many domains; in this course, we explore these approaches to classifiers, embeddings, and sequence-modeling applications.  Students will explore (and implement!) the cross-product of network shapes, training strategy, training corpora, and evaluation targets.  Neural networks -- like many objective-driven approaches -- are notoriously opaque to inspection, so this course will have a special focus on adaptation and domain-adaptable models and the reuse or re-training of existing models.

Catalog Description: 
In-depth study of a particular area of computational linguistics, with hands-on experience. Prerequisite: LING 570 and 571, or permission of instructor. Offered: WSp.
Credits: 
3.0
Status: 
Active
Last updated: 
January 10, 2018 - 9:12pm