Abstract

Machine translation of human languages is a field almost as old as computers themselves. Recent approaches to this challenging problem aim at learning translation knowledge automatically (or semi-automatically) from online text corpora, especially human-translated documents. For some language pairs, substantial translation resources exist, and these corpus-based systems can perform well. But for most language pairs, data is scarce, andcurrent techniques do not work well. To examine the gap betweenhuman and machine translators, we created an experiment in which humanbeings were asked to translate an unknown language into English on thesole basis of a very small bilingual text. Participants performed quite well,and debriefings revealed a number of valuable strategies. We discuss thesestrategies and apply some of them to a statistical translation system.

Date

January 1, 1970

Authors

Yaser Al-Onaizan, Ulrich Germann, Ulf Hermjakob, Kevin Knight, Philipp Koehn, Daniel Marcu, Kenji Yamada

Journal

Machine translation

Volume

17

Pages

1-17

Publisher

Kluwer Academic Publishers