Abstract
In this paper, we present a multilingual machine translation system for closed captions for digital television. To cope with frequent appearance of unregistered words and the articles of multiple domains as in TV news program, we propose a Dynamic Dictionary Adaptation method. We adopted live resources of multilingual Named Entities and their translingual equivalences from Web sites of daily news, providing multilingual daily news in Chinese, English, Japanese and Korean. We also utilize Dynamic Domain Identification for automatic dictionary stacking. With these integrated approaches, we obtained average translation quality enhancement of 0.5 in Mean Opinion Score (MOS) for Korean-to-Chinese. We also had 0.5 and 0.1 average enhancement for Korean-English and Korean-Japanese, respectively. The average enhancement is 0.37, which means almost a third level up to the next higher MOS scale.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Popowich, F., McFetridge, P., Nichoson, D., Toole, J.: Machine translation of closed captions. Machine Translation 15, 311–341 (2000)
Turcato, D., Popowich, F., McFetridge, P., Nicholson, D., Toole, J.: Pre-processing closed captions for machine translation. In: Proc. 3rd Workshop on Interlinguas and Interlingual Approaches, Seattle, Washington, pp. 38–45 (2000)
Nyberg, E., Mitamura, T.: A real-time MT system for translating broadcast captions. In: Proc. Machine Translation Summit VI, San Diego, USA, October 29-November 1, pp. 51–57 (1997)
Yang, S.-I., Kim, Y.-K., Seo, Y.-A., Choi, S.-K., Park, S.-K.: Korean to English TV caption translator: ”CaptionEye/KE”. In: Proc. 6th Natural Language Processing Pacific Rim Symposium (NLPRS), Tokyo, Japan, November 27-30, pp. 639–645 (2001)
Kim, T.-W., Sim, C.-M., Yuh, S.-H., Jung, H.-M., Kim, Y.-K., Choi, S.-K., Park, D.-I., Choi, K.-S.: FromTo-CLIR: web-based natural language interface for cross-language information retrieval. Int. Journal of Information Processing and Management 35(4), 559–586 (1999)
Huang, F., Vogel, S., Waibel, A.: Automatic extraction of named entity translingual equivalences based on multi-feature cost minimization. In: Proc. 41st Annual Meeting of the Association for Computational Linguistics (ACL), Joint Workshop on Multilingual and Mixed-Language Named Entity Recognition: Combining Statistical and Symbolic Models, Sapporo, Japan, July 12, pp. 9–16 (2003)
Electronic Industries Alliance: Digital Television (DTV) Closed Captioning (EIA-708-B), Electronic Industries Alliance (EIA) (December 1999)
Yuh, S.-H., Lee, K.-J., Seo, J.-Y.: Multilingual closed caption translation system for digital television. IEICE Trans. on Information and Systems E89-D(6), 1885–1892 (2006)
Lin, C.-Y., Hovy, E.: Automatic evaluation of summaries using N-gram co-occurrence statistics. In: Proc. 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology, Edmonton, Canada, vol. 1, pp. 71–78 (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Yuh, S., Seo, J. (2006). Multilingual Machine Translation of Closed Captions for Digital Television with Dynamic Dictionary Adaptation. In: Matsumoto, Y., Sproat, R.W., Wong, KF., Zhang, M. (eds) Computer Processing of Oriental Languages. Beyond the Orient: The Research Challenges Ahead. ICCPOL 2006. Lecture Notes in Computer Science(), vol 4285. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11940098_44
Download citation
DOI: https://doi.org/10.1007/11940098_44
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-49667-0
Online ISBN: 978-3-540-49668-7
eBook Packages: Computer ScienceComputer Science (R0)