We present a discriminative structureprediction model for the letter-to-phoneme task, a crucial step in text-to-speech processing. Our method encompasses three tasks that have bee...
Sittichai Jiampojamarn, Colin Cherry, Grzegorz Kon...
Abstract--Some recent publications have proposed methodologies to assess the performance of multimedia services in introducing subjective estimate of the end-to-end quality of vari...
In this paper we present a regression-based machine learning approach to email thread summarization. The regression model is able to take advantage of multiple gold-standard annot...
Jan Ulrich, Giuseppe Carenini, Gabriel Murray, Ray...
Abstract During the last decade research groups as well as a number of commercial software developers have started to deploy embodied conversational characters in the user interfac...
While storytelling has long been recognized as an important part of effective knowledge management in organizations, knowledge management technologies have generally not distingui...