“…The models used for comparison include NBT-DNN , NBT-CNN (Mrksic et al, 2017), Scalable (Rastogi et al, 2017), MemN2N (Liu and Perez, 2017), PtrNet (Xu andHu, 2018), LargeScale (Ramadan et al, 2018), GLAD (Ramadan et al, 2018), GCE (Nouri and Hosseini-Asl, 2018), StateNetPSI (Ren et al, 2018), SUMBT , HyST (Goel et al, 2019), DSTRead+JST (Gao et al, 2019), TRADE (Wu et al, 2019), COMER (Ren et al, 2019), DSTQA (Zhou and Small, 2019), MERET (Huang et al, 2020) and SST (Chen et al, 2020).…”