Latent Variable Models (LVM), like the Shared-GPLVM
and the Spectral Latent Variable Model, help mitigate over-
fitting when learning discriminative methods from small or
modera...
In this paper, we present a structural learning model for joint sentiment classification and aspect analysis of text at various levels of granularity. Our model aims to identify ...
During face-to-face conversation, people naturally integrate speech, gestures and higher level language interpretations to predict the right time to start talking or to give backc...
Abstract. We present a discriminatively trained model for joint modelling of object class labels (e.g. “person”, “dog”, “chair”, etc.) and their visual attributes (e.g....
Large-scale discriminative machine translation promises to further the state-of-the-art, but has failed to deliver convincing gains over current heuristic frequency count systems....