Using POS Information for Statistical Machine Translation into Morphologically Rich Languages

Abstract

When translating from languages with hardly any inflectional morphology like English into morphologically rich languages, the English word forms often do not contain enough information for producing the correct fullform in the target language. We investigate methods for improving the quality of such translations by making use of part-ofspeech information and maximum entropy modeling. Results for translations from English into Spanish and Catalan are presented on the LC-STAR corpus which consists of spontaneously spoken dialogues in the domain of appointment scheduling and travel planning.

Extracted Key Phrases

6 Figures and Tables

Cite this paper

@inproceedings{Ueffing1984UsingPI, title={Using POS Information for Statistical Machine Translation into Morphologically Rich Languages}, author={Nicola Ueffing and Hermann Ney}, year={1984} }