The output of handwritten word recognizers (WR) tends to be very noisy due to various factors. In order to compensate for this behaviour, several choices of the WR must be initial...
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...
Previous works tend to compute the similarity between two sentences based on the comparison of their nearest meanings. However, the nearest meanings do not always represent their ...
We present Minimum Bayes-Risk (MBR) decoding for statistical machine translation. This statistical approach aims to minimize expected loss of translation errors under loss functio...
In adding syntax to statistical MT, there is a tradeoff between taking advantage of linguistic analysis, versus allowing the model to exploit linguistically unmotivated mappings l...