Current hidden Markov acoustic modeling for large vocabulary continuous speech recognition (LVCSR) relies on the availability of abundant labeled transcriptions. Given that speech...
We propose a language-independent method for the automatic extraction of transliteration pairs from parallel corpora. In contrast to previous work, our method uses no form of supe...
Large vocabulary speech recognition systems fail to recognize words beyond their vocabulary, many of which are information rich terms, like named entities or foreign words. Hybrid...
Carolina Parada, Mark Dredze, Abhinav Sethy, Ariya...
In this paper, we investigate whether semantic relationships between entities can be learnt from analyzing microblog posts published on Twitter. We identify semantic links between ...
This article explores traditional conceptualizations of credibility relying on quantitative and qualitative analyses of data collected by the Institute for the Future of the Book,...