A Primer in BERTology: What We Know About How BERT Works

Anna Rogers, Olga Kovaleva, Anna Rumshisky

    Publikation: Artikel i tidsskrift og konference artikel i tidsskriftTidsskriftartikelForskningpeer review


    Transformer-based models have pushed state of the art in many areas of NLP, but our understanding of what is behind their success is still limited. This paper is the first survey of over 150 studies of the popular BERT model. We review the current state of knowledge about how BERT works, what kind of information it learns and how it is represented, common modifications to its training objectives and architecture, the overparameterization issue, and approaches to compression. We then outline directions for future research.
    TidsskriftTransactions of the Association for Computational Linguistics
    Sider (fra-til)842-866
    Antal sider25
    StatusUdgivet - 1 dec. 2020


    Dyk ned i forskningsemnerne om 'A Primer in BERTology: What We Know About How BERT Works'. Sammen danner de et unikt fingeraftryk.