Time Schedule:
Fei Xia
LING 572
Seattle Campus
Statistical approaches to applications such as machine translation, automated lexical acquisition (monolingual and bilingual), information retrieval, and question answering, with components including language modeling, alignment, and document clustering. Prerequisite: LING 570. Offered: W.
Class description
In this course, we will study statistical algorithms that produce state-of-the-art results on NLP tasks. We will compare supervised learning algorithms that require a lot of training data with the unsupervised ones. We will also study a few important discriminative models. Students will gain hands-on experience by applying these algorithms to real NLP tasks.
Student learning goals
General method of instruction
Recommended preparation
Prerequisites: LING 570 and LING 571 Stat 391 (Prob. and Stats for CS) or equivalent Programming: - C/C++ or Java - basic unix/linux commands (e.g., ls, cd, ln, sort, head) - Perl (optional): tutorials on Perl
Class assignments and grading
