This paper describes a methodology for constructing aligned German-Chinese corpora from movie subtitles. The corpora will be used to train a special machine translation system with intention to automatically translate the subtitles between German and Chinese. Since the common length-based algorithm for alignment shows weakness on short spoken sentences, especially on those from different language families, this paper studies to use dynamic programming based on time-shift information in subtitles, and extends it with statistical lexical cues to align the subtitle. In our experiment with around 4,000 Chinese and German sentences, the proposed alignment approach yields 83.8% precision. Furthermore, it is unrelated to languages, and leads to a general method of parallel corpora building between different language families.


sentence alignment parallel corpora lexical cues 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Brown, P., Lai, J.C., Mercer, R.: Aligning Sentences in Parallel Corpora. In: Proceedings of the 29th annual meeting on Association for Computational Linguistics, Berkeley, California, pp. 169–176 (1991)Google Scholar
  2. 2.
    Wu, D.K.: Aligning a Parallel English-Chinese Corpus Statistically with Lexical Criteria. In: Proceedings of the 32th Annual Conference of the Association for Computational Linguistics, Las Cruces, New Mexico, pp. 80–87 (1994)Google Scholar
  3. 3.
    Shemtov, H.: Text Aligment in a Tool for Translating Revised Documents. In: Proceedings of the 6th Conference on European Chapter of the Association for Computational Linguistics, Utrecht, The Netherlands, pp. 449–453 (1993)Google Scholar
  4. 4.
    Armstrong, S., Way, A., Caffrey, C., Flanagan, M., Kenny, D., O’Hagan, M.: Improving the Quality of Automated DVD Subtitles via Example-based Machine Translation. In: Proceedings of Translating and the Computer, Aslib, London, vol. 28 (2006)Google Scholar
  5. 5.
    Martin, V.: The Automatic Translation of Film Subtitles. A Machine Translation Success Story? In: Resourceful Language Technology: Festschrift in Honor of Anna, vol. 7. Uppsala University (2008)Google Scholar
  6. 6.
    Mathieu, M., Emmanuel, G.: Multilingual Aligned Corpora from Movie Subtitles. Rapport interne LISTIC, p. 6 (2005)Google Scholar
  7. 7.
    Vandeghinste, V., Sang, E.K.: Using a Parallel Transcript/Subtitle Corpus for Sentence Compression. In: LREC, Lisbon, Portugal (2004)Google Scholar
  8. 8.
    Popowich, F., McFetridge, P., Turcato, D., Toole, J.: Machine translation of Closed Captions. Machine Translation 15, 311–341 (2000)CrossRefGoogle Scholar
  9. 9.
    Och, F., Ney, H.: Improved Statistical Alignment Models. In: Proceedings of the 38th Annual Meeting of the Association for Computational Linguistics, pp. 440–447 (2000)Google Scholar
  10. 10.
    Lavecchia, C., Smaïli, K., Langlois, D.: Building Parallel Corpora from Movies. In: 5th International Workshop on Natural Language Processing and Cognitive Science, Funchal, Portugal (2007)Google Scholar
  11. 11.
    Tiedemann, J.: Improved Sentence Alignment for Movie Subtitles. In: Proceedings of the 12th Recent Advances in Natural Language Processing, Borovets, Bulgaria, pp. 582–588 (2007)Google Scholar
  12. 12.
    Reinhard, R.: Automatic Identification of Word Translations from Unrelated English and German Corpora. In: Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics, College Park, Maryland, pp. 519–526 (1999)Google Scholar
  13. 13.
    Gale, W.A., Church, K.W.: A Program for Aligning Sentences in Bilingual Corpora. Computational Linguistics 19(1), 75–102 (1993)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Han Xiao
    • 1
  • Xiaojie Wang
    • 2
  1. 1.School of Information EngineeringBeijing University of Post and TelecommunicationsChina
  2. 2.CISTRBeijing University of Post and TelecommunicationsChina

Personalised recommendations