Sentence-Permuted Paragraph Generation

04/15/2021
by   Wenhao Yu, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

09/26/2017

Generating Sentences by Editing Prototypes

We propose a new generative model of sentences that first samples a prot...
08/19/2019

Long and Diverse Text Generation with Planning-based Hierarchical Variational Model

Existing neural methods for data-to-text generation are still struggling...
09/04/2021

Pushing Paraphrase Away from Original Sentence: A Multi-Round Paraphrase Generation Approach

In recent years, neural paraphrase generation based on Seq2Seq has achie...
06/14/2019

Comparison of Diverse Decoding Methods from Conditional Language Models

While conditional language models have greatly improved in their ability...
07/23/2018

Influence of Selective Exposure to Viewing Contents Diversity

Personalization, including both self-selected and pre-selected, is inevi...
08/13/2018

D-PAGE: Diverse Paraphrase Generation

In this paper, we investigate the diversity aspect of paraphrase generat...
11/11/2018

ReDecode Framework for Iterative Improvement in Paraphrase Generation

Generating paraphrases, that is, different variations of a sentence conv...

Code Repositories