conftrace_

reward imitation learning

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

summary generation (1) answer generation (1) question-answer pair (1) question-answer generation (1) differentiable reward (1) answer accuracy (1) exposure bia (1) news recommendation (1) reward function (1) question generation (1)

Papers

Generating Self-Contained and Summary-Centric Question Answer Pairs via Differentiable Reward Imitation Learning EMNLP 2021