ISCA Archive IWSLT 2011
ISCA Archive IWSLT 2011

Modeling punctuation prediction as machine translation

Stephan Peitz, Markus Freitag, Arne Mauser, Hermann Ney

Punctuation prediction is an important task in Spoken Language Translation. The output of speech recognition systems does not typically contain punctuation marks. In this paper we analyze different methods for punctuation prediction and show improvements in the quality of the final translation output. In our experiments we compare the different approaches 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 unpunctuated 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.


Cite as: Peitz, S., Freitag, M., Mauser, A., Ney, H. (2011) Modeling punctuation prediction as machine translation. Proc. International Workshop on Spoken Language Translation (IWSLT 2011), 238-245

@inproceedings{peitz11_iwslt,
  author={Stephan Peitz and Markus Freitag and Arne Mauser and Hermann Ney},
  title={{Modeling punctuation prediction as machine translation}},
  year=2011,
  booktitle={Proc. International Workshop on Spoken Language Translation (IWSLT 2011)},
  pages={238--245}
}