Generalization in NLI: Ways (Not) To Go Beyond Simple Heuristics

Prajjwal Bhargava, Aleksandr Drozd, Anna Rogers

    Publikation: Konference artikel i Proceeding eller bog/rapport kapitelKonferencebidrag i proceedingsForskningpeer review

    Abstract

    Much of recent progress in NLU was shown to be due to models' learning dataset-specific heuristics. We conduct a case study of generalization in NLI (from MNLI to the adversarially constructed HANS dataset) in a range of BERT-based architectures (adapters, Siamese Transformers, HEX debiasing), as well as with subsampling the data and increasing the model size. We report 2 successful and 3 unsuccessful strategies, all providing insights into how Transformer-based models learn to generalize.
    OriginalsprogEngelsk
    TitelProceedings of the Second Workshop on Insights from Negative Results in NLP
    Antal sider11
    UdgivelsesstedOnline and Punta Cana, Dominican Republic
    ForlagAssociation for Computational Linguistics
    Publikationsdato1 nov. 2021
    Sider125-135
    StatusUdgivet - 1 nov. 2021

    Fingeraftryk

    Dyk ned i forskningsemnerne om 'Generalization in NLI: Ways (Not) To Go Beyond Simple Heuristics'. Sammen danner de et unikt fingeraftryk.

    Citationsformater