|
Abstract:
|
Natural language processing (NLP) is an area of computer science concerned with the application of computational methods to linguistic data. Examples of application areas within NLP include automatic (machine) translation between languages, dialogue systems, and information extraction. NLP problems offer a rich problem domain for statistical approaches; they often require the modeling of complex, discrete structures such as strings, labeled sequences, or trees. Generative statistical models, such as hidden Markov models or probabilistic context-free grammars, are a very common approach for this kind of problem. In this talk, I'll focus on recently proposed alternatives to generative statistical models. In particular, I'll describe generalizations of discriminative linear models, such as support vector machines or the perceptron algorithm, to structured problems found in NLP.
|
