In this paper we study the problem of finding most topical named entities among all entities in a document, which we refer to as focused named entity recognition. We show that th...
A concept of linearly graded statistical models for analogue performance evaluation is proposed and a suitable technique for automatic generation of analogue performance models us...
One commonly used approach for language recognition is to convert the input speech into a sequence of tokens such as words or phones and then to use these token sequences to deter...
Recently, instead of selecting a single kernel, multiple kernel learning (MKL) has been proposed which uses a convex combination of kernels, where the weight of each kernel is opt...
We describe a discriminatively trained sequence alignment model based on the averaged perceptron. In common with other approaches to sequence modeling using perceptrons, and in co...