Abstract
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.
Keywords
Cite this article
@article{cai-111161,
author = {Marta R. Costa-Jussa and Jose A. R. Fonollosa and Jose B. Marino and Marc Poch and Mireia Farrus},
title = {A Large Spanish-Catalan Parallel Corpus Release for Machine Translation},
journal = {Computing and Informatics},
volume = {33},
number = {4},
pages = {907--920},
year = {2014},
issn = {1335-9150},
url = {https://cai.type.sk/content/2014/4/a-large-spanish-catalan-parallel-corpus-release-for-machine-translation/}
}
TY - JOUR AU - Marta R. Costa-Jussa AU - Jose A. R. Fonollosa AU - Jose B. Marino AU - Marc Poch AU - Mireia Farrus TI - A Large Spanish-Catalan Parallel Corpus Release for Machine Translation JO - Computing and Informatics VL - 33 IS - 4 SP - 907 EP - 920 PY - 2014 SN - 1335-9150 UR - https://cai.type.sk/content/2014/4/a-large-spanish-catalan-parallel-corpus-release-for-machine-translation/ KW - Catalan-Spanish parallel corpus KW - machine translation ER -
Costa-Jussa, M. R., Fonollosa, J. A. R., Marino, J. B., Poch, M., & Farrus, M. (2014). A Large Spanish-Catalan Parallel Corpus Release for Machine Translation. Computing and Informatics, 33(4), 907–920. https://cai.type.sk/content/2014/4/a-large-spanish-catalan-parallel-corpus-release-for-machine-translation/