Name tagging is a critical early stage in many natural language processing pipelines. In this paper we analyze the types of errors produced by a tagger, distinguishing name classi...
This paper provides an overview of experiments carried out at the TREC 2004 Terabyte Track using the Indri search engine. Indri is an efficient, effective distributed search engin...
Donald Metzler, Trevor Strohman, Howard R. Turtle,...
When reasoning about complex domains, where information available is usually only partial, nonmonotonic reasoning can be an important tool. One of the formalisms introduced in thi...
Perceptron training is widely applied in the natural language processing community for learning complex structured models. Like all structured prediction learning frameworks, the ...
This paper presents a novel spatio-temporal Markov random field (MRF) for video denoising. Two main issues are addressed in this paper, namely, the estimation of noise model and t...