Conversational Agents have been shown to be effective tutors in a wide range of educational domains. However, these agents are often ignored and abused in collaborative learning s...
Mobile peer-to-peer groups, which do not require any pre-deployed infrastructure or trusted centralized authority are valuable for a variety of collaborative applications. This wor...
We present a phrasal synchronous grammar model of translational equivalence. Unlike previous approaches, we do not resort to heuristics or constraints from a word-alignment model,...
Phil Blunsom, Trevor Cohn, Chris Dyer, Miles Osbor...
It is usually assumed that the kind of noise existing in annotated data is random classification noise. Yet there is evidence that differences between annotators are not always ra...
In this paper, we propose a novel method for semi-supervised learning of nonprojective log-linear dependency parsers using directly expressed linguistic prior knowledge (e.g. a no...