@inproceedings{L16-1351,
 abstract = {This paper presents how an state-of-the-art SMT system is enriched by using an extra in-domain parallel corpora extracted from Wikipedia. We collect corpora from parallel titles and from parallel fragments in comparable articles from Wikipedia. We carried out an evaluation with a double objective: evaluating the quality of the extracted data and evaluating the improvement due to the domain-adaptation. We think this can be very useful for languages with limited amount of parallel corpora, where in-domain data is crucial to improve the performance of MT sytems. The experiments on the Spanish-English language pair improve a baseline trained with the Europarl corpus in more than 2 points of BLEU when translating in the Computer Science domain.
},
 address = {Portorož, Slovenia},
 author = {Gorka Labaka and Iñaki Alegria and Kepa Sarasola},
 booktitle = {Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016)},
 month = {May},
 pages = {2209--2213},
 publisher = {European Language Resources Association (ELRA)},
 title = {Domain Adaptation in MT Using Titles in Wikipedia as a Parallel Corpus: Resources and Evaluation},
 url = {https://www.aclweb.org/anthology/L16-1351},
 year = {2016}
}