Churnalist: Fictional Headline Generation for Context-appropriate Flavor Text

Judith van Stegeren, Mariet Theune

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

    77 Downloads (Pure)

    Abstract

    We present Churnalist, a headline generator for creating contextually-appropriate fictional headlines that can be used as ‘flavor text’ in games. Churnalist creates new headlines from existing headlines with text modification. It extracts seed words from free text input, queries a knowledge base for related words and uses these words in the new headlines. Churnalist’s knowledge base consists of a dataset of pre-trained word embeddings, thus requiring no linguistic expertise or hand-coded models from the user.
    Original languageEnglish
    Title of host publicationProceedings of the 10th International Conference on Computational Creativity
    EditorsKazjon Grace, Michael Cook, Dan Ventura, Mary Lou Maher
    PublisherAssociation for Computational Creativity
    Pages65-72
    Number of pages8
    ISBN (Electronic)978-989-54160-1-1
    Publication statusPublished - Jun 2019
    Event10th International Conference on Computational Creativity - UNC Charlotte, Charlotte, United States
    Duration: 17 Jun 201921 Jun 2019
    http://computationalcreativity.net/iccc2019/

    Conference

    Conference10th International Conference on Computational Creativity
    Abbreviated titleICCC 2019
    CountryUnited States
    CityCharlotte
    Period17/06/1921/06/19
    Internet address

    Keywords

    • natural language generation
    • text modification
    • headline generation
    • procedural content generation
    • text generation
    • video games
    • flavor text
    • computational creativity

    Fingerprint Dive into the research topics of 'Churnalist: Fictional Headline Generation for Context-appropriate Flavor Text'. Together they form a unique fingerprint.

  • Cite this

    van Stegeren, J., & Theune, M. (2019). Churnalist: Fictional Headline Generation for Context-appropriate Flavor Text. In K. Grace, M. Cook, D. Ventura, & M. L. Maher (Eds.), Proceedings of the 10th International Conference on Computational Creativity (pp. 65-72). Association for Computational Creativity.