@inproceedings{68bc1843cbec4cff83950e303b55d2bc,
title = "Enabling medical translation for low-resource languages",
abstract = "We present research towards bridging the language gap between migrant workers in Qatar and medical staff. In particular, we present the first steps towards the development of a real-world Hindi-English machine translation system for doctor-patient communication. As this is a low-resource language pair, especially for speech and for the medical domain, our initial focus has been on gathering suitable training data from various sources. We applied a variety of methods ranging from fully automatic extraction from the Web to manual annotation of test data. Moreover, we developed a method for automatically augmenting the training data with synthetically generated variants, which yielded a very sizable improvement of more than 3 BLEU points absolute.",
keywords = "Doctor-patient communication, Hindi, Machine translation, Medical translation, Resource-poor languages",
author = "Ahmad Musleh and Nadir Durrani and Irina Temnikova and Preslav Nakov and Stephan Vogel and Osama Alsaad",
note = "Publisher Copyright: {\textcopyright} Springer International Publishing AG, part of Springer Nature 2018.; 17th International Conference on Intelligent Text Processing and Computational Linguistics, CICLing 2016 ; Conference date: 03-04-2016 Through 09-04-2016",
year = "2018",
doi = "10.1007/978-3-319-75487-1_1",
language = "English",
isbn = "9783319754864",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "3--16",
editor = "Alexander Gelbukh",
booktitle = "Computational Linguistics and Intelligent Text Processing - 17th International Conference, CICLing 2016, Revised Selected Papers",
address = "Germany",
}