The TÜBİTAK-UEKAE Statistical Machine Translation System for IWSLT 2008
2008
We present the TUBITAK-UEKAE statistical machine translation system that participated in the IWSLT 2008 evaluation campaign. Our system is based on the opensource phrase-based statistical machine translation software Moses. Additionally, phrase-table augmentation is applied to maximize source language coverage; lexical approximation is applied to replace out-of-vocabulary words with known words prior to decoding; and automatic punctuation insertion is improved. We describe the preprocessing and postprocessing steps and our training and decoding procedures. Results are presented on our participation in the classical Arabic-English and Chinese-English tasks as well as the new Chinese-Spanish direct and Chinese-EnglishSpanish pivot translation tasks.
Keywords:
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
9
References
1
Citations
NaN
KQI