Advanced search


Mara Chinea-Rios. Estrategias de aprendizaje online de los pesos del modelo log-lineal en traducción automática interactiva. Master Inteligencia Artificial, Reconocimiento de Formas e Imagen Digital. 2013. Advisors: Germán Sanchis-Trilles and Francisco Casacuberta

In a post-edit scenario, the translations obtained by machine translator systems need to have been corrected by a human translator to obtain the desire quality. Interactive Machine Tranlation (IMT) paradigm is able to reduce the effort and the time that human translators have to invert in the correction process. In this thesis, we propose to adapt the weights of the log-linear model in interactive machine translator. For adapting the weights of the log-linear model, we have utilizes different online learning algorithms. The main goal is that the system learns from the errors corrected. We propose to use three different online learning algorithms: Discriminative Ridge Regression, Passive Agressive and Percetron-Like. These algorithms has been used in post-edit scenario with good results. These algorithms needed a new formulation in IMT scenario. With these new formulations, we have obtained different results. These resuts give the posibility to use the new formulations to archieve the quality deseared and reduce efforts of the human translator in new problems.