Sequence Transduction: Generalization and Challenges

by Thamme Gowda in Note tags: NMT
Sequence to sequence transduction is a general problem, for which many other problems are special cases. I also highlight some challenges of this general problem. more…

Many-to-English Machine Translation Tools, Data, and Pretrained Models

by Thamme Gowda in Paper tags: NMT
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. more…

Macro-Average: Rare Types Are Important Too

by Thamme Gowda in Paper tags: NMT
We explore the simple type-based classifier metric, \maf1, and study its applicability to MT evaluation. \ more…

Finding the Optimal Vocabulary for Neural Machine Translation

by Thamme Gowda in Paper tags: NMT
We cast neural machine translation (NMT) as a classification task in an autoregressive setting and analyze the limitations of both classification and autoregression components. \ more…