A new Bayesian model is proposed, integrating dictionary learning and topic modeling into a unified framework. The model is applied to cluster multiple images, and a subset of th...
Lingbo Li, Mingyuan Zhou, Eric Wang, Lawrence Cari...
In this work, we try a hybrid methodology for language modeling where both morphological decomposition and factored language modeling (FLM) are exploited to deal with the complex ...
Effectively assisting people in complex and highly dynamic work environment requires advances in high-level declarative activity models that can describe the flow of human work act...
Duration of phonemic segments provide important cues for distinguishing words in languages such as Arabic. Recently, we proposed a discriminatively estimated joint acoustic, durat...
This paper shows that discriminative reranking with an averaged perceptron model yields substantial improvements in realization quality with CCG. The paper confirms the utility of...