Structured Prediction

Instructor: Shashank Srivastava
ssrivastava@cs.unc.edu

When: Mondays 10:40 am-1:10 pm
Where: Zoom Link https://unc.zoom.us/j/98373740557 (see important information regarding using Zoom here)
Office hours: Fridays, 2-3pm (by appointment)

Sign up on course Piazza (Access code is comp790)

Sign-up for paper presentations here!

Course overview

This is a research-oriented course on structured prediction, which is the class of prediction problems where the output is constrained by some structure. These include labeling, alignment, parsing, ranking and segmentation problems over structures such as sequences, trees and graphs. The main focus of the course will be on problems from natural language processing, although the methods have applications in many domains (computer vision, computational biology, social media analysis, information retrieval, etc.).

The course will involve weekly paper readings and a project. We will explore both recent research and foundational methods in this area. The tentative list of topics that we will cover is:

• Structures: sequences, trees, graphs.

• Practical concerns in predicting structures

• Linear Sequence models: HMMs, MEMMs, CRFs

• Structured Perceptron and Large-margin methods (M3Ns, Structured SVMs)

• Inference methods: Dynamic Programming, Graph algo, ILPs, Sampling

• Structured Prediction and Graphical Models

• Variational Inference, Latent Variable Modeling

• Deep Structured Prediction, Deep Generative Models

• Optimization: SGD, EM, Dual Decomposition, AD3

• Learning to Search and RL: DAgger & SEARN-like methods

Prerequisites:

This course assumes previous experience with Machine Learning (prior exposure to NLP will be a plus), although there are no formal pre-requisites. If you have taken such classes before, feel free to take the course. If you are uncertain, you should email me.

Class Schedule (tentative):