ACL 2022long34 citations

A Well-Composed Text is Half Done! Composition Sampling for Diverse Conditional Generation

Shashi Narayan, Gonçalo Simões, Yao Zhao, Joshua Maynez, Dipanjan Das, Michael Collins, Mirella Lapata

Abstract

We propose Composition Sampling, a simple but effective method to generate diverse outputs for conditional generation of higher quality compared to previous stochastic decoding strategies. It builds on recently proposed plan-based neural generation models (FROST, Narayan et al, 2021) that are trained to first create a composition of the output and then generate by conditioning on it and the input. Our approach avoids text degeneration by first sampling a composition in the form of an entity chain and then using beam search to generate the best possible text grounded to this entity chain. Experiments on summarization (CNN/DailyMail and XSum) and question generation (SQuAD), using existing and newly proposed automaticmetrics together with human-based evaluation, demonstrate that Composition Sampling is currently the best available decoding strategy for generating diverse meaningful outputs.

BibTeX
@inproceedings{narayan-etal-2022-well,
    title = "A Well-Composed Text is Half Done! Composition Sampling for Diverse Conditional Generation",
    author = "Narayan, Shashi  and
      Sim{\~o}es, Gon{\c{c}}alo  and
      Zhao, Yao  and
      Maynez, Joshua  and
      Das, Dipanjan  and
      Collins, Michael  and
      Lapata, Mirella",
    editor = "Muresan, Smaranda  and
      Nakov, Preslav  and
      Villavicencio, Aline",
    booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = may,
    year = "2022",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.acl-long.94/",
    doi = "10.18653/v1/2022.acl-long.94",
    pages = "1319--1339"
}
A Well-Composed Text is Half Done! Composition Sampling for Diverse Conditional Generation · ACL 2022