Attention

publications

Publication Image
On the weak link between importance and prunability of attention heads

Aakriti Budhraja , Madhura Pande , Preksha Nema & more

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

http://dx.doi.org/10.18653/v1/2020.emnlp-main.260
Publication Image
On the Importance of Local Information in Transformer Based Models

Madhura Pande , Aakriti Budhraja , Preksha Nema & more

arXiv:2008.05828

https://arxiv.org/pdf/2008.05828.pdf
Publication Image
Towards Transparent and Explainable Attention Models

Akash Kumar Mohankumar , Preksha Nema , Sharan Narasimhan & more

In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics.

https://doi.org/10.18653/v1/2020.acl-main.387
Publication Image
Attend, Adapt and Transfer: Attentive Deep Architecture for Adaptive Transfer from multiple sources

Janarthanan Rajendran , Aravind Lakshminarayanan , Mitesh M Khapra & more

arXiv preprint arXiv:1510.02879