Many-to-English Machine Translation Tools, Data, and Pretrained Models
This work addresses the gap in translation tools for many low-resource languages, though it is incremental as it builds on existing multilingual translation approaches.
The authors tackled the problem of limited machine translation support for low-resource languages by developing tools and a multilingual model that translates from 500 source languages to English, making it available for download and transfer learning.
While there are more than 7000 languages in the world, most translation research efforts have targeted a few high-resource languages. Commercial translation systems support only one hundred languages or fewer, and do not make these models available for transfer to low resource languages. In this work, we present useful tools for machine translation research: MTData, NLCodec, and RTG. We demonstrate their usefulness by creating a multilingual neural machine translation model capable of translating from 500 source languages to English. We make this multilingual model readily downloadable and usable as a service, or as a parent model for transfer-learning to even lower-resource languages.