In NMT we search for the mode of the model distribution to form predictions. The mode and
other high-probability translations found by beam search have been shown to often be …

Many applications within natural language processing involve performing text-to-text
transformations, ie, given a text in natural language as input, systems are required to …

Abstract We present Minimum Bayes-Risk (MBR) decoding over translation lattices that
compactly encode a huge number of translation hypotheses. We describe conditions on the …

In NMT we search for the mode of the model distribution to form predictions. The mode and
other high-probability translations found by beam search have been shown to often be …

We present a generative probabilistic model, inspired by historical printing processes, for
transcribing images of documents from the printing press era. By jointly modeling the text of …

The impact of computer systems that can understand natural language will be tremendous.
To develop this capability we need to be able to automatically and efficiently analyze large …

Abstract Minimum Error Rate Training (MERT) and Minimum Bayes-Risk (MBR) decoding
are used in most current state-of-theart Statistical Machine Translation (SMT) systems. The …

In this article we address the issue of generating diversified translation systems from a single
Statistical Machine Translation (SMT) engine for system combination. Unlike traditional …

Word reordering is a difficult task for translation between languages with widely different
word orders, such as Japanese and English. A previously proposed post-ordering method …

Efficiency is a prime concern in syntactic MT decoding, yet significant developments in
statistical parsing with respect to asymptotic efficiency haven't yet been explored in MT …