RUG-1-Pegasussers at SemEval-2022 Task 3: Data Generation Methods to Improve Recognizing Appropriate Taxonomic Word Relations

Frank van den Berg, Gijs Danoe, Esther Ploeger, Wessel Poelman, Lukas Edman, Tommaso Caselli

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

    1 Citation (Scopus)
    27 Downloads (Pure)

    Abstract

    This paper describes our system created for the SemEval 2022 Task 3: Presupposed Taxonomies - Evaluating Neural-network Semantics. This task is focused on correctly recognizing taxonomic word relations in English, French and Italian. We develop various data generation techniques that expand the originally provided train set and show that all methods increase the performance of models trained on these expanded datasets. Our final system outperforms the baseline from the task organizers by achieving an average macro F1 score of 79.6 on all languages, compared to the baseline's 67.4.

    Original languageEnglish
    Title of host publicationSemEval 2022 - 16th International Workshop on Semantic Evaluation, Proceedings of the Workshop
    EditorsGuy Emerson, Natalie Schluter, Gabriel Stanovsky, Ritesh Kumar, Alexis Palmer, Nathan Schneider, Siddharth Singh, Shyam Ratan
    PublisherAssociation for Computational Linguistics, ACL Anthology
    Pages247-254
    Number of pages8
    ISBN (Electronic)9781955917803
    DOIs
    Publication statusPublished - 2022
    Event16th International Workshop on Semantic Evaluation, SemEval 2022 - Seattle, United States
    Duration: 14-Jul-202215-Jul-2022

    Publication series

    NameSemEval 2022 - 16th International Workshop on Semantic Evaluation, Proceedings of the Workshop

    Conference

    Conference16th International Workshop on Semantic Evaluation, SemEval 2022
    Country/TerritoryUnited States
    CitySeattle
    Period14/07/202215/07/2022

    Cite this