Work

Six Challenges for Neural Machine Translation

Year: 2017
Type: conference-paper
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 phrasebased statistical machine translation.
Language: English
Open Access status: gold
OpenAlex ID: W2625092622
FWCI: 56.98
Cites: 32
Cited by: 1,676
Related to: 10