Generating paragraphs of diverse contents is important in many applications. Existing generation models produce similar contents from homogenized contexts due to the fixed left-to-right sentence order. Our idea is permuting the sentence orders to improve the content diversity of multi-sentence paragraph. We propose a novel framework PermGen whose objective is to maximize the expected log-likelihood of output paragraph distributions with respect to all possible sentence orders. PermGen uses hierarchical positional embedding and designs new procedures for training, decoding, and candidate ranking in the sentence-permuted generation. Experiments on three paragraph generation benchmarks demonstrate PermGen generates more diverse outputs with a higher quality than existing models.
@article{arxiv.2104.07228,
title = {Sentence-Permuted Paragraph Generation},
author = {Wenhao Yu and Chenguang Zhu and Tong Zhao and Zhichun Guo and Meng Jiang},
journal= {arXiv preprint arXiv:2104.07228},
year = {2021}
}