Abstract
For several reasons machine translation systems are today unsuited to process long texts in one shot. In particular, in statistical machine translation, heuristic search algorithms are employed whose level of approximation depends on the length of the input. Moreover, processing time can be a bottleneck with long sentences, whereas multiple text chunks can be quickly processed in parallel. Hence, in real working conditions the problem arises of how to optimally split the input text. In this work, we investigate several text segmentation criteria and verify their impact on translation performance by means of a statistical phrase-based translation system. Experiments are reported on a popular as well as difficult task, namely the translation of news agencies from Chinese-English as proposed by the NIST MT evaluation workshops. Results reveal that best performance can be achieved by taking into account both linguistic and input length constraints.
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
Berger, A., Della Pietra, S.A., Della Pietra, V.J.: A Maximum Entropy Approach to Natural Language Processing. Computational Linguistics 22(1), 39–71 (1996)
Och, F.J., Ney, H.: Discriminative training and maximum entropy models for stati stical machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, PA, Philadelphia, USA (2002)
Brown, P.F., Della Pietra, S.A., Della Pietra, V.J., Mercer, R.L.: The Mathematics of Statistical Machine Translation: Parameter Estimation. Computational Linguistics 19(2), 263–312 (1993)
Och, F.J.: Minimum error rate training in statistical machine translation. In: Proceedings of the 41st Meeting of the Association for Computational Linguistics (ACL), Sapporo, Japan, pp. 160–167 (2003)
Cettolo, M., Federico, M.: Minimum Error Training of Log-Linear Translation Models. In: Proceedings of the International Workshop on Spoken Language Translation (IWSLT), Kyoto, Japan, September 2004, pp. 103–106 (2004), http://www.slt.atr.jp/IWSLT2004/archives/000619.html
Och, F.J., Ney, H.: Improved Statistical Alignment Models. In: Proceedings of the 38th Annual Meeting of the Association for Computational Linguistics, Hong Kong, China (2000)
Chen, B., Cattoni, R., Bertoldi, N., Cettolo, M., Federico, M.: The ITC-irst SMT System for IWSLT 2005. In: Proceedings of IWSLT (2005), http://www.is.cs.cmu.edu/iwslt2005/proceedings.html
Tran, B.H., Seide, F., Steinbiss, V.: A Word Graph based N-Best Search in Continuous Speech Recognition. In: Proceedings of ICLSP (1996)
Federico, M., Bertoldi, N.: A word-to-phrase statistical translation model. ACM Transaction on Speech Language Processing 2(2), 1–24 (2005)
Papineni, K., Roukos, S., Ward, T., Zhu, W.-J.: Bleu: a Method for Automatic Evaluation of Machine Translation. Research Report RC22176, IBM Research Division, Thomas J. Watson Research Center (2001)
Doddington, G.: Automatic Evaluation of Machine Translation Quality using N-gram Co-occurrence Statistics. In: Proceedings of the ARPA Workshop on Human Language Technology (2002)
Matusov, E., Leusch, G., Bender, O., Ney, H.: Evaluating Machine Translation Output with Automatic Sentence Segmentation. In: Proceedings of IWSLT (2005), http://www.is.cs.cmu.edu/iwslt2005/proceedings.html
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
Cettolo, M., Federico, M. (2006). Text Segmentation Criteria for Statistical Machine Translation. In: Salakoski, T., Ginter, F., Pyysalo, S., Pahikkala, T. (eds) Advances in Natural Language Processing. FinTAL 2006. Lecture Notes in Computer Science(), vol 4139. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11816508_66
Download citation
DOI: https://doi.org/10.1007/11816508_66
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-37334-6
Online ISBN: 978-3-540-37336-0
eBook Packages: Computer ScienceComputer Science (R0)