Automated learning of templates for data-to-text generation: comparing rule-based, statistical and neural methods

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

    Abstract

    The current study investigated novel techniques and methods for trainable approaches to data-to-text generation. Neural Machine Translation was explored for the conversion from data to text as well as the addition of extra templatization steps of the data input and text output in the conversion process. Evaluation using BLEU did not find the Neural Machine Translation technique to perform any better compared to rule-based or Statistical Machine Translation, and the templatization method seemed to perform similarly or sometimes worse compared to direct data-to-text conversion. However, the human evaluation metrics indicated that Neural Machine Translation yielded the highest quality output and that the templatization method was able to increase text quality in multiple situations.
    Original languageEnglish
    Title of host publicationProceedings of the 11th International Conference on Natural Language Generation
    PublisherAssociation for Computational Linguistics (ACL)
    Pages35- 45
    Number of pages10
    DOIs
    Publication statusPublished - 2018
    Event11th International Conference on Natural Language Generation - Tilburg University, Tilburg, Netherlands
    Duration: 5 Nov 20188 Nov 2018
    Conference number: 11
    https://inlg2018.uvt.nl/

    Conference

    Conference11th International Conference on Natural Language Generation
    Abbreviated titleINLG 2018
    Country/TerritoryNetherlands
    CityTilburg
    Period5/11/188/11/18
    Internet address

    Keywords

    • data-to-text generation
    • Neural Machine Translation
    • Templatization method

    Fingerprint

    Dive into the research topics of 'Automated learning of templates for data-to-text generation: comparing rule-based, statistical and neural methods'. Together they form a unique fingerprint.

    Cite this