The Heads Hypothesis: A Unifying Statistical Approach Towards Understanding Multi-Headed Attention in BERT.
Madhura Pande, Aakriti Budhraja, Preksha Nema, Pratyush Kumar, Mitesh M. Khapra
Browse the full AAAI paper archive.
Madhura Pande, Aakriti Budhraja, Preksha Nema, Pratyush Kumar, Mitesh M. Khapra
Browse the full AAAI paper archive.