Abstract. Automated Text Categorization has reached the levels of accuracy of human experts. Provided that enough training data is available, it is possible to learn accurate autom...
Many data mining applications have a large amount of data but labeling data is often difficult, expensive, or time consuming, as it requires human experts for annotation. Semi-supe...
Appearance-based methods, based on statistical models of the pixel values in an image (region) rather than geometrical object models, are increasingly popular in computer vision. I...
This paper presents a partial matching strategy for phrase-based statistical machine translation (PBSMT). Source phrases which do not appear in the training corpus can be translat...
Current statistical machine translation (SMT) systems are trained on sentencealigned and word-aligned parallel text collected from various sources. Translation model parameters ar...
Spyros Matsoukas, Antti-Veikko I. Rosti, Bing Zhan...