Natural sounds are structured on many time-scales. A typical segment of speech, for example, contains features that span four orders of magnitude: Sentences (∼1 s); phonemes (...
It is becoming more important to design systems capable of performing high-level management and control tasks in interactive dynamic environments. At the same time, it is difficul...
We present a novel paradigm for statistical machine translation (SMT), based on a joint modeling of word alignment and the topical aspects underlying bilingual document-pairs, via...
We argue that multilingual parallel data provides a valuable source of indirect supervision for induction of shallow semantic representations. Specifically, we consider unsupervi...
Self-explaining is a beneficial learning strategy for studying worked-out examples because it either supplies missing information through the generation of inferences or because it...
Robert G. M. Hausmann, Timothy J. Nokes, Kurt VanL...