Selecting a representative output via range voting over beam search candidates improves BLEU, length, and diversity in image captioning and machine translation.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Leveraging Sentence Similarity in Natural Language Generation: Improving Beam Search using Range Voting
Selecting a representative output via range voting over beam search candidates improves BLEU, length, and diversity in image captioning and machine translation.