Achieving Open Vocabulary Neural Machine Translation with Hybrid Word-Character Models

Understand

Nearly all previous work on neural machine translation (NMT) has used quite restricted vocabularies, perhaps with a subsequent method to patch in unknown words.

• This paper presents a novel word-character solution to achieving open vocabulary NMT.
• We build hybrid systems that translate mostly at the word level and consult the character components for rare words.
• Our character-level recurrent neural networks compute source word representations and recover unknown target words when needed.