We address the problem of generating multiple hypotheses for structured prediction tasks that involve interaction with users or successive components in a cascaded architecture. Given a set of multiple hypotheses, such components/users typically have the ability to retrieve the best (or approximately the best) solution in this set. The standard approach for handling such a scenario is to first ...

This paper provide a structured analysis of US Supreme Court Oral Hearings to enable identification of the relevant issues, factors and facts that can be used to construct a test to resolve a case. Our analysis involves the production of what we term ‘argument component trees’ (ACTs) in which the issues, facts and factors, and the relationship between these, are made explicit. We show how such ...

In this thesis we address structured machine learning problems. Here “structured” refers to situations in which the input or output domain of a prediction function is non-vectorial. Instead, the input instance or the predicted value can be decomposed into parts that follow certain dependencies, relations and constraints. Throughout the thesis we will use hard computer vision tasks as a rich sou...

In problems where input features have varying amounts of noise, using distinct regularization hyperparameters for different features provides an effective means of managing model complexity. While regularizers for neural networks and support vector machines often rely on multiple hyperparameters, regularizers for structured prediction models (used in tasks such as sequence labeling or parsing) ...

Input-output analysis of transitional channel flows has proven to be a valuable analytical tool for identifying important flow structures and energetic motions. The traditional approach abstracts the nonlinear terms as forcing that is unstructured, in sense this not directly tied underlying nonlinearity dynamics. This paper instead employs structured singular value-based preserves certain input...

We propose a structured prediction architecture for images centered around deep recurrent neural networks. The proposed network, called ReSeg, is based on the recently introduced ReNet model for object classification. We modify and extend it to perform object segmentation, noting that the avoidance of pooling can greatly simplify pixel-wise tasks for images. The ReSeg layer is composed of four ...