Theoretical analysis of bus-invert coding for reducing switching activity was previously investigated. In this paper we conduct a theoretical analysis of this method for coupling r...
We describe an approach to the computation of symbolic resultants in which factors are removed during the course of the calculation, so reducing the stack size required for interme...
Most attempts to train part-of-speech taggers on a mixture of labeled and unlabeled data have failed. In this work stacked learning is used to reduce tagging to a classification t...
We introduce an extension to CCG that allows form and function to be represented simultaneously, reducing the proliferation of modifier categories seen in standard CCG analyses. W...
Recognizer Output Voting Error Reduction (ROVER), is a well-known procedure for decoders’ combination aiming at reducing the Word Error Rate (WER) in transcription applications....