1 code implementation • 25 Oct 2022 • Han Meng, Xiaosong He, Zexing Chen, Feng Zhou
Some Natural Language Generation (NLG) tasks require both faithfulness and diversity.
1 code implementation • 22 Dec 2020 • Erfan Nozari, Maxwell A. Bertolero, Jennifer Stiso, Lorenzo Caciagli, Eli J. Cornblath, Xiaosong He, Arun S. Mahadevan, George J. Pappas, Dani Smith Bassett
Contrary to our expectations, linear auto-regressive models achieve the best measures across all three metrics, eliminating the trade-off between accuracy and simplicity.