Pande, M., Budhraja, A., Nema, P., Kumar, P., & Khapra, M. M. (2021). The Heads Hypothesis: A Unifying Statistical Approach Towards Understanding Multi-Headed Attention in BERT. Proceedings of the AAAI Conference on Artificial Intelligence, 35(15), 13613-13621. https://doi.org/10.1609/aaai.v35i15.17605