“…These have included rule-based approaches (McKeown, 1979;Meteer and Shaked, 1988) and data-driven methods (Madnani and Dorr, 2010), with recently the most common approach being that the task is treated as a language translation task (Bannard and Callison-Burch, 2005;Barzilay and McKeown, 2001;Pang et al, 2003) -often performed using a bilingual corpus pivoting back and forth (Madnani and Dorr, 2010;Prakash et al, 2016;Mallinson et al, 2017). Other methods proposed include more recently the use of Deep Reinforcement Learning (Li et al, 2018) , supervised learning using sequence-to-sequence models (Gupta et al, 2018;Prakash et al, 2016) and unsupervised approaches (Bowman et al, 2016;Roy and Grangier, 2019).…”