Максимальное правдоподобие с наградой
method
ID: rewardaugmentedmaximumlikelihood
Related Papers
Ensure the Correctness of the Summary: Incorporate Entailment Knowledge into Abstractive Sentence Summarization
AbstractIn this paper, we investigate the sentence summarization task that produces a summary from a source sentence. Neural sequence-to-sequence models have gained considerable success for this task, while most existing …...