BERT | Robert Bosch Center for Data Science and Artificial Intelligence

publications

The heads hypothesis: A unifying statistical approach towards understanding multi-headed attention in BERT

The heads hypothesis: A unifying statistical approach towards understanding multi-headed attention in BERT

Madhura Pande , Aakriti Budhraja , Preksha Nema and more

To appear in the Proceedings of the Thirty-Fifth Annual Conference of the Association for Advancement of Artificial Intelligence (AAAI 2021)

Improving Dialog Evaluation with a Multi-reference Adversarial Dataset and Large Scale Pretraining

Improving Dialog Evaluation with a Multi-reference Adversarial Dataset and Large Scale Pretraining

Ananya B. Sai , Akash Kumar Mohankumar , Siddhartha Arora and Mitesh M. Khapra

Transactions of the Association for Computational Linguistics

On the weak link between importance and prunability of attention heads

On the weak link between importance and prunability of attention heads

Aakriti Budhraja , Madhura Pande , Preksha Nema and more

In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing . Association for Computational Linguistics.

Towards Interpreting BERT for Reading Comprehension Based QA

Towards Interpreting BERT for Reading Comprehension Based QA

Sahana Ramnath , Preksha Nema , Deep Sahni and more

In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics.

On Incorporating Structural Information to improve Dialogue Response Generation

On Incorporating Structural Information to improve Dialogue Response Generation

Nikita Moghe , Priyesh Vijayan , Balaraman Ravindran and more

arXiv:2005.14315