Models of Morphosyntax for Statistical Machine Translation -- Morphosyntaktische Modelle für statistische maschinelle Übersetzung

Models of Morphosyntax for Statistical Machine Translation

Statistical approaches to machine translation (MT) have shown themselves to be effective in the last few years. However, when translating into a morphologically rich language this is not true, particularly when there is also significant syntactic divergence between the two languages. The quality of statistical machine translation is poor in this case because of independence assumptions made between the models of morphology, syntax and translation that do not reflect linguistic reality.

The project uses advances in automatic linguistic analysis of syntax and morphology to advance statistical MT. The dependencies between morphology, syntax and translation are directly modeled. This leads to the creation of translation models and search algorithms that dramatically improve translation quality for morphologically rich languages.

Funded by the German Research Foundation


Principal Investigators

Dr. Alexander Fraser

Prof. Dr. Hinrich Schuetze

Present Staff

Anita Ramm (nee Gojun)

Marion Di Marco (nee Weller)

Past Staff

Fabienne Braune

Fabienne Cap (nee Fritzinger)

Nadir Durrani

Patrick Leucht

Hassan Sajjad

Nina Seemann

Renjing Wang