The TÜBİTAK statistical machine translation system for IWSLT 2012

Coşkun Mermer, Hamza Kaya, İlknur Durgar El-Kahlout, Mehmet Uğur Doğan


Abstract
WedescribetheTU ̈B ̇ITAKsubmissiontotheIWSLT2012 Evaluation Campaign. Our system development focused on utilizing Bayesian alignment methods such as variational Bayes and Gibbs sampling in addition to the standard GIZA++ alignments. The submitted tracks are the Arabic-English and Turkish-English TED Talks translation tasks.
Anthology ID:
2012.iwslt-evaluation.20
Volume:
Proceedings of the 9th International Workshop on Spoken Language Translation: Evaluation Campaign
Month:
December 6-7
Year:
2012
Address:
Hong Kong, Table of contents
Venue:
IWSLT
SIG:
SIGSLT
Publisher:
Note:
Pages:
144–148
Language:
URL:
https://aclanthology.org/2012.iwslt-evaluation.20
DOI:
Bibkey:
Cite (ACL):
Coşkun Mermer, Hamza Kaya, İlknur Durgar El-Kahlout, and Mehmet Uğur Doğan. 2012. The TÜBİTAK statistical machine translation system for IWSLT 2012. In Proceedings of the 9th International Workshop on Spoken Language Translation: Evaluation Campaign, pages 144–148, Hong Kong, Table of contents.
Cite (Informal):
The TÜBİTAK statistical machine translation system for IWSLT 2012 (Mermer et al., IWSLT 2012)
Copy Citation:
PDF:
https://preview.aclanthology.org/autopr/2012.iwslt-evaluation.20.pdf