We present a machine translation framework that can incorporate arbitrary features of both input and output sentences. The core of the approach is a novel decoder based on lattice...
In this paper, we present a semi-supervised method for automatic speech act recognition in email and forums. The major challenge of this task is due to lack of labeled data in the...
Syntactic reordering on the source-side is an effective way of handling word order differences. The (DE) construction is a flexible and ubiquitous syntactic structure in Chinese w...
Research in named entity recognition and mention detection has typically involved a fairly small number of semantic classes, which may not be adequate if semantic class informatio...
Recently, almost uncontrolled technological progress allows so called high-throughput data collection for sophisticated and complex experimental biological systems analysis. Espec...