We propose a method for providing stochastic confidence estimates for rule-based and black-box natural language (NL) processing systems. Our method does not require labeled trainin...
Christian Monson, Kristy Hollingshead, Brian Roark
We propose a novel objective function for discriminatively tuning log-linear machine translation models. Our objective explicitly optimizes the BLEU score of expected n-gram count...
There are several kinds of non-invasive imaging methods that are used to collect data from the brain, e.g., EEG, MEG, PET, SPECT, fMRI, etc. It is difficult to get resolution of i...
Recent advances in statistical machine translation have used approximate beam search for NP-complete inference within probabilistic translation models. We present an alternative ap...
Abhishek Arun, Barry Haddow, Philipp Koehn, Adam L...
Recently there has been interest in structured discriminative models for speech recognition. In these models sentence posteriors are directly modelled, given a set of features ext...