Then, for imagecaptioning task, common practice [1,13,15,28,30]further adopts CIDEr-based trainingobjectiveusingreinforcementtraining[24]toimprovetheperformanceofimagecaptioning

Paraphrase generation aims to synthesize paraphrases of a given sentence automatically. We use the official splits to report our results. Thus, there are 6513, 497 and 2,990 video clips in trainingset,validationsetandtestset,respectively. Following theSelf-Critical Sequence Training [24](SCST), thegradient ofLRL(θ)canbe approximatedby θLRL(θ) (r(ys1:T) r(ˆy1:T)) θlogpθ(ys1:T) (3) where r(ys1:T) is the score of a sampled captionys1:T and r(ˆy1:T) suggests the baseline score of a caption which is generated by the current model using greedy decode. Distilling knowledge learned inBERTfortext generation. A deep generative framework for paraphrase generation.