The TALP-UPC Phrase-Based Translation Systems for WMT13: System Combination with Morphology Generation, Domain Adaptation and Corpus Filtering

@inproceedings{Formiga2013TheTP,
  title={The TALP-UPC Phrase-Based Translation Systems for WMT13: System Combination with Morphology Generation, Domain Adaptation and Corpus Filtering},
  author={Llu{\'i}s Formiga and Marta R. Costa-Juss{\`a} and Jos{\'e} B. Mari{\~n}o and Jos{\'e} A. R. Fonollosa and Alberto Barr{\'o}n-Cede{\~n}o and Llu{\'i}s M{\`a}rquez i Villodre},
  booktitle={WMT@ACL},
  year={2013}
}
This paper describes the TALP participation in the WMT13 evaluation campaign. Our participation is based on the combination of several statistical machine translation systems: based on standard phrasebased Moses systems. Variations include techniques such as morphology generation, training sentence filtering, and domain adaptation through unit derivation. The results show a coherent improvement on TER, METEOR, NIST, and BLEU scores when compared to our baseline system.