We present a perceptron-style discriminative approach to machine translation in which large feature sets can be exploited. Unlike discriminative reranking approaches, our system c...
Consider the problem of joint parameter estimation and prediction in a Markov random field: i.e., the model parameters are estimated on the basis of an initial set of data, and th...
We propose a real time single item auction based task allocation method for the multi-robot exploration problem and investigate new bid evaluation strategies in this domain. In th...
This paper presents an approach for building consensus ontologies from the individual ontologies of a network of socially interacting agents. Each agent has its own conceptualizat...
A substantial subset of the web data follows some kind of underlying structure. In order to let software programs gain full benefit from these “semistructured” web sources, wra...