Minimum error rate training (MERT) involves choosing parameter values for a machine translation (MT) system that maximize performance on a tuning set as measured by an automatic e...
In Chinese texts, words composed of single or multiple characters are not separated by spaces, unlike most western languages. Therefore Chinese word segmentation is considered an ...
In this paper, we propose an unsupervised approach to automatically synthesize Wikipedia articles in multiple languages. Taking an existing high-quality version of any entry as co...
This paper describes an approach for computing a consensus translation from the outputs of multiple machine translation (MT) systems. The consensus translation is computed by weigh...
Evgeny Matusov, Gregor Leusch, Rafael E. Banchs, N...
The main feature of the free online-encyclopedia Wikipedia is the wiki-tool, which allows viewers to edit the articles directly in the web browser. As a weakness of this openness ...