AggGen: Ordering and aggregating while generating

Xinnuo Xu, Ondrej Dušek, Verena Rieser, Ioannis Konstas

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

7 Citations (Scopus)
58 Downloads (Pure)

Abstract

We present AggGen (pronounced 'again'), a data-to-text model which re-introduces two explicit sentence planning stages into neural data-to-text systems: input ordering and input aggregation. In contrast to previous work using sentence planning, our model is still end-to-end: AggGen performs sentence planning at the same time as generating text by learning latent alignments (via semantic facts) between input representation and target text. Experiments on the WebNLG and E2E challenge data show that by using fact-based alignments our approach is more interpretable, expressive, robust to noise, and easier to control, while retaining the advantages of end-to-end systems in terms of fluency. Our code is available at https://github.com/XinnuoXu/AggGen.

Original languageEnglish
Title of host publicationProceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing
PublisherAssociation for Computational Linguistics
Pages1419-1434
Number of pages16
Volume1
ISBN (Electronic)9781954085527
DOIs
Publication statusPublished - Aug 2021
EventJoint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing - Virtual, Online
Duration: 1 Aug 20216 Aug 2021

Conference

ConferenceJoint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing
Abbreviated titleACL-IJCNLP 2021
CityVirtual, Online
Period1/08/216/08/21

ASJC Scopus subject areas

  • Software
  • Computational Theory and Mathematics
  • Linguistics and Language
  • Language and Linguistics

Fingerprint

Dive into the research topics of 'AggGen: Ordering and aggregating while generating'. Together they form a unique fingerprint.

Cite this