UPC-BMIC-VDU system description for the IWSLT 2010: testing several collocation segmentations in a phrase-based SMT system

2010 International Workshop on Spoken Language Translation, IWSLT 2010

Volumn , Issue , 2010, Pages 189-195

  Henríquez, Carlos A Q ^a   Costa Jussà, Marta R ^b   Daudaravicius, Vidas ^c   Banchs, Rafael E ^d   Mariño, José B ^a  

^a UNIVERSITAT POLITÈCNICA DE CATALUNYA   (Spain)

^b Barcelona Media Innovation Center   (Spain)

^c VYTAUTAS MAGNUS UNIVERSITY   (Lithuania)

^d INSTITUTE FOR INFOCOMM RESEARCH   (Singapore)

Author keywords

[No Author keywords available]

Indexed keywords

CHI-SQUARED; HIGH FREQUENCY HF; HIGH-FREQUENCY WORDS; LOG LIKELIHOOD; LOWER FREQUENCIES; MUTUAL INFORMATIONS; SMT SYSTEMS; STATISTICAL MEASURES; SYSTEM DESCRIPTION; TRANSLATION UNIT;

EID: 85133170942     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (14)

1. F. Casacuberta. Finite-state transducers for speech input translation. In Proc. IEEE ASRU, Madonna di Campiglio, Italy, 2001.
2. Y. Choueka. Looking for needles in a haystack or locating interesting collocational expressions in large textual databases. In RIAO, pages 609–624, 1988.
3. M.R. Costa-jussà, V. Daudaravicius, and R. E. Banchs. Integration of statistical collocation segmentations in a phrase-based statistical machine translation system. In 14th Annual meeting of the EAMT: European Association for Machine Translation, Saint-Raphael, 2010.
4. V. Daudaravicius. The influence of collocation segmentation and top 10 items to keyword assignment performance. In 11th International Conference on Intelligent Text Processing and Computational Linguistics, Springer Verlag, LNCS, pages 648–660, Iasi, Romania, 2010.
5. V. Daudaravicius and R Marcinkeviciene. Gravity counts for the boundaries of collocations. International Journal of Corpus Linguistics, 9(2):321–348, 2004.
6. I. García-Varea, D. Ortiz, F. Nevado, P.A. Gómez, and F. Casacuberta. Automatic segmentation of bilingual corpora: A comparison of different techniques. In Iberian Conference on Pattern Recognition and Image Analysis, volume 3523 of Lecture Notes in Computer Science, pages 614–621. Springer-Verlag, Estoril (Portugal), June 2005.
7. C. A. Henríquez Q., M. R. Costa-jussà, V. Daudaravicius, Rafael E. Banchs, and J. B. Mariño. Using collocation segmentation to augment the phrase table. In Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR, pages 104–108, Uppsala, Sweden, July 2010.
8. J. B. Mariño, R. E. Banchs, J. M. Crego, A. de Gispert, P. Lambert, J. A.R. Fonollosa, and M. R. Costa-jussà. N-gram based machine translation. Computational linguistics, 32(4):527–549, 2006.
9. F. Nevado and F. Casacuberta. Bilingual corpora segmentation using bilingual recursive alignments. In Proceedings of the 3th Jornadas en Tecnología del Habla, Valencia, 2004.
10. F.J. Och and H. Ney. The alignment template approach to statistical machine translation. Computational linguistics, 30(4):417–449, December 2004.
11. P. Pecina and P. Schlesinger. Combining association measures for collocation extraction. In Proceedings of the COLING/ACL on Main conference poster sessions, pages 651–658, Morristown, NJ, USA, 2006. Association for Computational Linguistics.
12. F. Smadja. Retrieving collocations from text: Xtract. Computational Linguistics, 19(1):143–177, 1993.
13. T. Takezawa, E. Sumita, F. Sugaya, H. Yamamoto, and S. Yamamoto. Toward a broad-coverage bilingual corpus for speech translation of travel conversations in the real world. In Proceeding of LREC-2002: Third International Conference on Language Resources and Evaluation, pages 147–152, Las Palmas, Spain, May 2002.
14. Y. Zhang, S. Vogel, and A. Waibel. Automatic segmentation of bilingual corpora: A comparison of different techniques. In Natural Language Processing and Knowledge Engineering, 2003. Proceedings, pages 567–573. 2003.