@article{Costa-Jussà_Fonollosa_Mariño_Poch_Farrús_2015, title={A Large Spanish-Catalan Parallel Corpus Release for Machine Translation}, volume={33}, url={https://www.cai.sk/ojs/index.php/cai/article/view/2807}, abstractNote={We present a large Spanish-Catalan parallel corpus extracted from ten years of the paper edition of a bilingual Catalan newspaper. The produced corpus of 7.5 M parallel sentences (around 180 M words per language) is useful for many natural language applications. We report excellent results when building a statistical machine translation system trained on this parallel corpus. The Spanish-Catalan corpus is partially available via ELDA (Evaluations and Language Resources Distribution Agency) in catalog number ELRA-W0053.}, number={4}, journal={COMPUTING AND INFORMATICS}, author={Costa-Jussà, Marta R. and Fonollosa, José A. R. and Mariño, José B. and Poch, Marc and Farrús, Mireia}, year={2015}, month={Feb.}, pages={907–920} }