no code implementations • CCNLG (ACL) 2019 • Subhajit Naskar, Soumya Saha, Sreeparna Mukherjee
Decoder
no code implementations • Findings (ACL) 2022 • Scott Novotney, Sreeparna Mukherjee, Zeeshan Ahmed, Andreas Stolcke
Training the model initially with proxy context retains 67% of the perplexity gain after adapting to real context.
Decoder Sentence