@inproceedings{L16-1094,
 abstract = {In this paper, we address the problem of Machine Translation (MT) for a specialised domain in a language pair for which only a very small domain-specific parallel corpus is available. We conduct a series of experiments using a purely phrase-based SMT (PBSMT) system and a hybrid MT system (TectoMT), testing three different strategies to overcome the problem of the small amount of in-domain training data. Our results show that adding a small size in-domain bilingual terminology to the small in-domain training corpus leads to the best improvements of a hybrid MT system, while the PBSMT system achieves the best results by adding a combination of in-domain bilingual terminology and a larger out-of-domain corpus. We focus on qualitative human evaluation of the output of two best systems (one for each approach) and perform a systematic in-depth error analysis which revealed advantages of the hybrid MT system over the pure PBSMT system for this specific task.
},
 address = {Portorož, Slovenia},
 author = {Sanja Štajner and Andreia Querido and Nuno Rendeiro and João António Rodrigues and António Branco},
 booktitle = {Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016)},
 month = {May},
 pages = {592--598},
 publisher = {European Language Resources Association (ELRA)},
 title = {Use of Domain-Specific Language Resources in Machine Translation},
 url = {https://www.aclweb.org/anthology/L16-1094},
 year = {2016}
}