We present two machine learning approaches to information extraction from semi-structured documents that can be used if no annotated training data are available, but there does ex...
arrhythmias (extended abstract) Elisa Fromont, Ren´e Quiniou, Marie-Odile Cordier We are interested in using parallel universes to learn interpretable models that can be subseque...
Speaker clustering is the task of grouping a set of speech utterances into speaker-specific classes. The basic techniques for solving this task are similar to those used for spea...
Abstract. Temporal random variation of luminance in images can manifest in film and video due to a wide variety of sources. Typical in archived films, it also affects scenes rec...
Conditional random fields (CRFs) are graphical models for modeling the probability of labels given the observations. They have traditionally been trained with using a set of obser...
Xinhua Zhang, Douglas Aberdeen, S. V. N. Vishwanat...