“…The skeleton could also be multiple keyphrases. The keyphrases are extracted based on word frequency (Ippolito et al, 2019;Tan et al, 2020;Wu et al, 2020), an off-the-shelf keyword extraction method (Peng et al, 2018;Goldfarb-Tarrant et al, 2019;Yao et al, 2019;Rashkin et al, 2020;Zhang et al, 2020), a sentence compression dataset and reinforcement learning (Xu et al, 2018), or image caption datasets and ConceptNet (Lin et al, 2020). Most of the studies focus on modeling the longterm dependency among the keyphrases and/or forcing the generation to contain the keyphrases.…”