Sentence-Permuted Paragraph Generation

TL;DR

This paper introduces PermGen, a novel paragraph generation framework that enhances content diversity by permuting sentence orders and optimizing across all possible permutations, leading to more diverse and higher-quality paragraphs.

Contribution

PermGen is the first model to maximize paragraph likelihood over all sentence permutations, improving diversity and quality in multi-sentence paragraph generation.

Findings

PermGen produces more diverse paragraphs than existing models.

PermGen achieves higher quality in generated content.

Experiments on three benchmarks validate PermGen's effectiveness.

Abstract

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.