Bill Byrne

Learn More
In recent years there has been growing interest in discriminative parameter training techniques, resulting from notable improvements in speech recognition performance on tasks ranging in size from digit recognition to Switchboard. Typified by Maximum Mutual Information (MMI) or Minimum Classification Error (MCE) training, these methods assume a fixed(More)
We present a simple preordering approach for machine translation based on a feature-rich logistic regression model to predict whether two children of the same node in the source-side parse tree should be swapped or not. Given the pair-wise children regression scores we conduct an efficient depth-first branch-and-bound search through the space of possible(More)
We propose the use of neural networks to model source-side preordering for faster and better statistical machine translation. The neu-ral network trains a logistic regression model to predict whether two sibling nodes of the source-side parse tree should be swapped in order to obtain a more monotonic parallel corpus, based on samples extracted from the(More)
The 'Language Modeling for Spontaneous Speech' (LMSS) project team at the 1995 Johns Hopkins Workshop (\LM'95") devoted its resources to addressing three major issues: analysis of the baseline Switchboard system, mod-eling of conversational speech phenomena, and preliminary investigation of \data bleaching" | a new domain adaptation paradigm. When analyzing(More)
This paper describes the use of pushdown automata (PDA) in the context of statistical machine translation and alignment under a synchronous context-free grammar. We use PDAs to compactly represent the space of candidate translations generated by the grammar when applied to an input sentence. General-purpose PDA algorithms for replacement, composition,(More)
This paper describes a novel method for automatically inserting filled pauses (e.g., UM) into fluent texts. Although filled pauses are known to serve a wide range of psychological and structural functions in conversational speech, they have not traditionally been modelled overtly by state-of-the-art speech synthesis systems. However, several recent systems(More)
We investigate the use of hierarchical phrase-based SMT lattices in end-to-end neural machine translation (NMT). Weight pushing transforms the Hiero scores for complete translation hypotheses, with the full translation grammar score and full n-gram language model score, into posteriors compatible with NMT predictive probabilities. With a slightly modified(More)
This paper presents the University of Cam-bridge submission to WMT16. Motivated by the complementary nature of syntac-tical machine translation and neural machine translation (NMT), we exploit the synergies of Hiero and NMT in different combination schemes. Starting out with a simple neural lattice rescoring approach, we show that the Hiero lattices are(More)