Plan and generate: Explicit and implicit variational augmentation for multi-document summarization of scientific articles

Pancheng Wang, Shasha Li, Shenling Liu, Jintao Tang, Ting Wang

Abstract: Highlights•We propose a novel sentence-level planning-based abstractive model for MDSS.•We augment the planning with neural topic mode and sequential latent variables.•Experimental results show that our model achieves state-of-the-art performance.