Machine Reading, Fast and Slow: When Do Models 'Understand' Language?

Sagnik Ray Choudhury, Anna Rogers, Isabelle Augenstein

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


    Two of the most fundamental issues in Natural Language Understanding (NLU) at present are: (a) how it can established whether deep learning-based models score highly on NLU benchmarks for the 'right' reasons; and (b) what those reasons would even be. We investigate the behavior of reading comprehension models with respect to two linguistic 'skills': coreference resolution and comparison. We propose a definition for the reasoning steps expected from a system that would be 'reading slowly', and compare that with the behavior of five models of the BERT family of various sizes, observed through saliency scores and counterfactual explanations. We find that for comparison (but not coreference) the systems based on larger encoders are more likely to rely on the 'right' information, but even they struggle with generalization, suggesting that they still learn specific lexical patterns rather than the general principles of comparison.
    TitelProceedings of the 29th International Conference on Computational Linguistics
    Antal sider16
    UdgivelsesstedGyeongju, Republic of Korea
    StatusUdgivet - 2022


    Dyk ned i forskningsemnerne om 'Machine Reading, Fast and Slow: When Do Models 'Understand' Language?'. Sammen danner de et unikt fingeraftryk.