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.
Original language | English |
---|---|
Title of host publication | Proceedings of the First Workshop on Neural Machine Translation |
Place of Publication | Vancouver, Canada |
Publisher | Association for Computational Linguistics |
Pages | 28-39 |
Number of pages | 12 |
ISBN (Print) | 978-1-945626-68-5 |
DOIs | |
Publication status | Published - 1 Aug 2017 |
Event | First Workshop on Neural Machine Translation - Vancouver, Canada Duration: 4 Aug 2017 → 4 Aug 2017 https://sites.google.com/site/acl17nmt/ |
Conference
Conference | First Workshop on Neural Machine Translation |
---|---|
Abbreviated title | NMT 2017 |
Country/Territory | Canada |
City | Vancouver |
Period | 4/08/17 → 4/08/17 |
Internet address |