Example-Based Incremental Synchronous Interpretation

This article describes a new approach to example based incremental translation for automatic interpretation systems developed in Verbmobil that reached 79% of approximately correct translations on speech recognition output.

Abstract

This article describes a new approach to example based incremental translation for automatic interpretation systems developed in Verbmobil. The translation module is completely learned from a bilingual corpus. The training phase combines statistical word alignment with precomputation of translation "chunks" and contextual clustering of syntactic equivalence classes (word classes). The system gives incremental output for every piece of input being it words or sequences of words. It thus tries to mimic the behaviour of a human synchronous interpreter. If a larger context leads to the need for reformulation the system utters a correction marker like I mean, and restarts the output from the starting position of the reformulation. The system is currently effective for German ⇔ English. German ⇔ Chinese and German a Japanese are under construction. In the Verbmobil evaluation, this approach reached 79% of approximately correct translations on speech recognition output.