We present a word alignment framework that can incorporate partial manual alignments.
The core of the approach is a novel semi-supervised algorithm extending the widely used …

We present a Bayesian approach to word alignment inference in IBM Models 1 and 2. In the
original approach, word translation probabilities (ie, model parameters) are estimated using …

Numerous empirical results have shown that combining data from multiple domains often
improve statistical machine translation (SMT) performance. For example, if we desire to build …

This paper describes our recent improvements to IBM TRANSTAC speech-to-speech
translation systems that address various issues arising from dealing with resource …

In most statistical machine translation (SMT) systems, bilingual segments are extracted via
word alignment. However, there is a need for systematic study as to what alignment …

One of the fundamental assumptions in statistical machine translation (SMT) is that the
correspondence between a sentence and its translation can be explained in terms of an …

This paper proposes a novel semisupervised word alignment technique called EMDC that
integrates discriminative and generative methods. A discriminative aligner is used to find …

In most statistical machine translation (SMT) systems, bilingual segments are extracted via
word alignment. However, there lacks systematic study as to what alignment characteristics …

Bitext alignment is the task of aligning a text in a source language and its translation in the
target language. Aligning amounts to finding the translational correspondences between …

The quality of statistical machine translation systems depends on the quality of the word
alignments, computed during the translation model training phase. IBM generative …