|Kristian Woodsend: "Optimize what you write, satisfy how you write it: Integer linear programming models for text rewriting"|
Fecha: martes 22 de enero de 2013
Lugar de celebración: Sala 1.03, ETSI Informática, UNED
Recent years have witnessed increased interest in data-driven methods for text rewriting, e.g., writing a document in a simpler style, or a sentence in more concise manner. It is frequently the case, when performing inference in these natural language tasks, that the decisions involved are mutually dependent. Local decision makers (such as machine-learning classifiers) have a role to play, but in order to make coherent decisions during inference, it is essential that takes these interdependencies into account. I will be giving a tutorial on how to develop Integer Linear Programming (ILP) models for inference, using models that we developed for text rewriting as examples. In these models, we combined the rules and predictions made through data-driven and machine learning methods, with declarative knowledge expressed as constraints.
Kristian Woodsend is currently a researcher at the University of Edinburgh. He has been working with Prof Mirella Lapata on natural language generation, on tasks such as summarization, generating highlights and captions, and simplification. This work has involved combining machine learning techniques with integer linear programming optimization methods which are able to explore the whole solution space efficiently and find the global optimum. Previously, he gained his PhD in large-scale numerical optimization methods for training support vector machines. Before that, he spent several years developing software for mobile phones.
Lugar de celebraciónSala 1.03ETSI Informática, UNEDc/ Juan del Rosal, 16Ciudad Universitaria28040 Madrid