Six Challenges for Neural Machine Translation
Preprint
Abstract
We explore six challenges for neural machine translation: domain mismatch, amount of training data, rare words, long sentences, word alignment, and beam search. We show both deficiencies and improvements over the quality of phrase-based statistical machine translation.Keywords
All Related Versions
This publication has 1 reference indexed in Scilit:
- Hierarchical Phrase-Based TranslationComputational Linguistics, 2007