Text generation with exemplar-based adaptive decoding

Hao Peng, Ankur P. Parikh, Manaal Faruqui, Bhuwan Dhingra, Dipanjan Das

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We propose a novel conditioned text generation model. It draws inspiration from traditional template-based text generation techniques, where the source provides the content (i.e., what to say), and the template influences how to say it. Building on the successful encoder-decoder paradigm, it first encodes the content representation from the given input text; to produce the output, it retrieves exemplar text from the training data as “soft templates,” which are then used to construct an exemplar-specific decoder. We evaluate the proposed model on abstractive text summarization and data-to-text generation. Empirical results show that this model achieves strong performance and outperforms comparable baselines.

Original languageEnglish (US)
Title of host publicationLong and Short Papers
PublisherAssociation for Computational Linguistics (ACL)
Pages2555-2565
Number of pages11
ISBN (Electronic)9781950737130
StatePublished - 2019
Externally publishedYes
Event2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2019 - Minneapolis, United States
Duration: Jun 2 2019Jun 7 2019

Publication series

NameNAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference
Volume1

Conference

Conference2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2019
Country/TerritoryUnited States
CityMinneapolis
Period6/2/196/7/19

ASJC Scopus subject areas

  • Language and Linguistics
  • Computer Science Applications
  • Linguistics and Language

Fingerprint

Dive into the research topics of 'Text generation with exemplar-based adaptive decoding'. Together they form a unique fingerprint.

Cite this