Abstract
This paper proposes an unsupervised word segmentation algorithm that identifies word boundaries in continuous source language text in order to improve the translation quality of statistical machine translation (SMT) approaches for the translation of local dialects by exploiting linguistic information of the standard language. The method iteratively learns multiple segmentation schemes that are consistent with (1) the standard dialect segmentations and (2) the phrasal segmentations of an SMT system trained on the resegmented bitext of the local dialect. In a second step multiple segmentation schemes are integrated into a single SMT system by characterizing the source language side and merging identical translation pairs of differently segmented SMT models. Experimental results translating three Japanese local dialects (Kumamoto, Kyoto, Osaka) into three Indo-European languages (English, German, Russian) revealed that the proposed system outperforms SMT engines trained on character-based as well as standard dialect segmentation schemes for the majority of the investigated translation tasks and automatic evaluation metrics.
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.
Similar content being viewed by others
References
Nerbonne, J., Heeringa, W.: Measuring Dialect Distance Phonetically. In: Proc. of the ACL SIG in Computational Phonology, Madrid, Spain, pp. 11–18 (1997)
Heeringa, W., Kleiweg, P., Gosskens, C., Nerbonne, J.: Evaluation of String Distance Algorithms for Dialectology. In: Proc. of the Workshop on Linguistic Distances, Sydney, Australia, pp. 51–62 (2006)
Scherrer, Y.: Adaptive String Distance Measures for Bilingual Dialect Lexicon Induction. In: Proc. of the ACL Student Research Workshop, Prague, Czech Republic, pp. 55–60 (2007)
Chitturi, R., Hansen, J.: Dialect Classification for online podcasts fusing Acoustic and Language-based Structural and Semantic Information. In: Proc. of the ACL-HLT (Companion Volume), Columbus, USA, pp. 21–24 (2008)
Habash, N., Rambow, O., Kiraz, G.: Morphological Analysis and Generation for Arabic Dialects. In: Proc. of the ACL Workshop on Computational Approaches to Semitic Languages, Ann Arbor, USA, pp. 17–24 (2005)
Chiang, D., Diab, M., Habash, N., Rainbow, O., Shareef, S.: Parsing Arabic Dialects. In: Proc. of the EACL, Trento, Italy, pp. 369–376 (2006)
Biadsy, F., Hirschberg, J., Habash, N.: Spoken Arabic Dialect Identification Using Phonotactic Modeling. In: Proc. of the EACL, Athens, Greek, pp. 53–61 (2009)
Weber, D., Mann, W.: Prospects for Computer-Assisted Dialect Adaption. American Journal of Computational Linguistics 7(3), 165–177 (1981)
Zhang, X., Hom, K.H.: Dialect MT: A Case Study between Cantonese and Mandarin. In: Proc. of the ACL-COLING, Montreal, Canada, pp. 1460–1464 (1998)
Sawaf, H.: Arabic Dialect Handling in Hybrid Machine Translation. In: Proc. of the AMTA, Denver, USA (2010)
Cheng, K.S., Young, G., Wong, K.F.: A study on word-based and integrat-bit Chinese text compression algorithms. American Society of Information Science 50(3), 218–228 (1999)
Venkataraman, A.: A statistical model for word discovery in transcribed speech. Computational Linguistics 27(3), 351–372 (2001)
Goldwater, S., Griffith, T., Johnson, M.: Contextual Dependencies in Unsupervised Word Segmentation. In: Proc. of the ACL, Sydney, Australia, pp. 673–680 (2006)
Chang, P.C., Galley, M., Manning, C.: Optimizing Chinese Word Segmentation for Machine Translation Performance. In: Proc. of the 3rd Workshop on SMT, Columbus, USA, pp. 224–232 (2008)
Xu, J., Gao, J., Toutanova, K., Ney, H.: Bayesian Semi-Supervised Chinese Word Segmentation for SMT. In: Proc. of the COLING, Manchester, UK, pp. 1017–1024 (2008)
Zhang, R., Yasuda, K., Sumita, E.: Improved Statistical Machine Translation by Multiple Chinese Word Segmentation. In: Proc. of the 3rd Workshop on SMT, Columbus, USA, pp. 216–223 (2008)
Dyer, C.: Using a maximum entropy model to build segmentation lattices for MT. In: Proc. of HLT, Boulder, USA, pp. 406–414 (2009)
Ma, Y., Way, A.: Bilingually Motivated Domain-Adapted Word Segmentation for Statistical Machine Translation. In: Proc. of the 12th EACL, Athens, Greece, pp. 549–557 (2009)
Berger, A., Pietra, S.D., Pietra, V.D.: A maximum entropy approach to NLP. Computational Linguistics 22(1), 39–71 (1996)
Pietra, S.D., Pietra, V.D., Lafferty, J.: Inducing Features of Random Fields. IEEE Transactions on Pattern Analysis and Machine Intelligence 19(4), 380–393 (1997)
Ratnaparkhi, A.: A Maximum Entropy Model for Part-Of-Speech Tagging. In: Proc. of the EMNLP, Pennsylvania, USA, pp. 133–142 (1996)
Kikui, G., Yamamoto, S., Takezawa, T., Sumita, E.: Comparative study on corpora for speech translation. IEEE Transactions on Audio, Speech and Language 14(5), 1674–1682 (2006)
Och, F.J., Ney, H.: A Systematic Comparison of Statistical Alignment Models. Computational Linguistics 29(1), 19–51 (2003)
Stolcke, A.: SRILM an extensible language modeling toolkit. In: Proc. of ICSLP, Denver, USA, pp. 901–904 (2002)
Finch, A., Denoual, E., Okuma, H., Paul, M., Yamamoto, H., Yasuda, K., Zhang, R., Sumita, E.: The NICT/ATR Speech Translation System. In: Proc. of the IWSLT, Trento, Italy, pp. 103–110 (2007)
Papineni, K., Roukos, S., Ward, T., Zhu, W.-J.: BLEU: a Method for Automatic Evaluation of Machine Translation. In: Proc. of the 40th ACL, Philadelphia, USA, pp. 311–318 (2002)
Snover, M., Dorr, B., Schwartz, R., Micciulla, L., Makhoul, J.: A study of translation edit rate with targeted human annotation. In: Proc. of the AMTA, Cambridge and USA, pp. 223–231 (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Paul, M., Finch, A., Sumita, E. (2011). Word Segmentation for Dialect Translation. In: Gelbukh, A. (eds) Computational Linguistics and Intelligent Text Processing. CICLing 2011. Lecture Notes in Computer Science, vol 6609. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-19437-5_5
Download citation
DOI: https://doi.org/10.1007/978-3-642-19437-5_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-19436-8
Online ISBN: 978-3-642-19437-5
eBook Packages: Computer ScienceComputer Science (R0)