Structured prediction is the problem of predicting multiple outputs with complex internal structure and dependencies among them. Algorithms and models for predicting structured data have been in use for a long time. For example, recurrent neural networks and hidden Markov models have found interesting applications in temporal pattern recognition problems such as speech recognition. With the introduction of support vector machines in the 1990s, there has been a lot of interest in the machine learning community in discriminative models of learning. In this tutorial, we plan to cover recent developments in discriminative learning algorithms for predicting structured data.

We believe this tutorial will be of interest to machine learning researchers including graduate students who would like to gain an understanding of structured prediction and state-of-the-art approaches to solve this problem. Structured prediction has several applications in the areas of natural language processing, computer vision and computational biology, just to name a few. We believe the material presented in this tutorial will also be of interest to researchers working in the aforementioned application areas.