Modeling Punctuation Prediction as Machine Translation

Punctuation prediction is an important task in Spoken Lan-guage Translation. The output of speech recognition systems does not typically contain punctuation marks. In this pa-per we analyze different methods for punctuation prediction and show improvements in the quality of the final transla-tion output. In our experiments we compare the different ap-proaches and show improvements of up to 0.8 BLEU points on the IWSLT 2011 English French Speech Translation of Talks task using a translation system to translate from un-punctuated to punctuated text instead of a language model based punctuation prediction method. Furthermore, we do a system combination of the hypotheses of all our different approaches and get an additional improvement of 0.4 points in BLEU. 1