We applied a structure learning model, Max-Margin Structure (MMS), to natural language processing (NLP) tasks, where the aim is to capture the latent relationships within the output language domain. We formulate this model as an extension of multi–class Support VectorMachine (SVM) and present a perceptron–based learning approach to solve the problem. Experiments are carried out on two related NLP tasks: part–of–speech (POS) tagging andmachine translation (MT), illustrating the effectiveness of the model.
|Translated title of the contribution||Structure learning for natural langauge processing|
|Title of host publication||the 11th IEEE International Workshop on Machine Learning Signal Processing, France|
|Publication status||Published - 2009|