|| Checking for direct PDF access through Ovid
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, and current techniques do not work well. To examine the gap between human and machine translators, we created an experiment in which human beings were asked to translate an unknown language into English on the sole basis of a very small bilingual text. Participants performed quite well, and debriefings revealed a number of valuable strategies. We discuss these strategies and apply some of them to a statistical translation system.