A reward function learned from human ratings, with no reference summaries, guides RL summarizers to produce summaries rated higher by humans than ROUGE-trained systems.
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
-
Better Rewards Yield Better Summaries: Learning to Summarise Without References
A reward function learned from human ratings, with no reference summaries, guides RL summarizers to produce summaries rated higher by humans than ROUGE-trained systems.