Semi-supervised classification uses aspects of both unsupervised and supervised learning to improve upon the performance of traditional classification methods. Semi-supervised clu...
Automatic repeat request (ARQ) schemes are effective to recover non-real-time data corrupted by channel errors, but their use with real-time traffic is seldom considered because p...
We address the task of unsupervised topic segmentation of speech data operating over raw acoustic information. In contrast to existing algorithms for topic segmentation of speech,...
Igor Malioutov, Alex Park, Regina Barzilay, James ...
We demonstrate the effectiveness of multilingual learning for unsupervised part-of-speech tagging. The key hypothesis of multilingual learning is that by combining cues from multi...
Benjamin Snyder, Tahira Naseem, Jacob Eisenstein, ...
Safety-critical medical work requires an error-minded approach for design of the technologies that support its processes. We define the requirements that such a framework should me...