Enabling Medical Translation for Low-Resource Languages
This addresses a practical communication barrier for migrant workers and medical staff in Qatar, though it appears incremental as it builds on existing translation techniques.
The researchers tackled the problem of doctor-patient communication for Hindi-English translation in Qatar by developing a machine translation system for this low-resource language pair, achieving a significant improvement of over 3 BLEU points through data augmentation methods.
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.