Search Results for author: Dhruv Agarwal

Found 5 papers, 3 papers with code

Entity Linking via Explicit Mention-Mention Coreference Modeling

1 code implementation NAACL 2022 Dhruv Agarwal, Rico Angell, Nicholas Monath, Andrew McCallum

Learning representations of entity mentions is a core component of modern entity linking systems for both candidate generation and making linking predictions.

 Ranked #1 on Entity Linking on MedMentions (Recall@64 metric)

Entity Linking Re-Ranking

From Multimodal to Unimodal Attention in Transformers using Knowledge Distillation

no code implementations15 Oct 2021 Dhruv Agarwal, Tanay Agrawal, Laura M. Ferrari, François Bremond

Multimodal Deep Learning has garnered much interest, and transformers have triggered novel approaches, thanks to the cross-attention mechanism.

Knowledge Distillation Multimodal Deep Learning

Entity Linking and Discovery via Arborescence-based Supervised Clustering

1 code implementation2 Sep 2021 Dhruv Agarwal, Rico Angell, Nicholas Monath, Andrew McCallum

Previous work has shown promising results in performing entity linking by measuring not only the affinities between mentions and entities but also those amongst mentions.

Entity Linking

Solving Physics Puzzles by Reasoning about Paths

2 code implementations14 Nov 2020 Augustin Harter, Andrew Melnik, Gaurav Kumar, Dhruv Agarwal, Animesh Garg, Helge Ritter

We propose a new deep learning model for goal-driven tasks that require intuitive physical reasoning and intervention in the scene to achieve a desired end goal.

Cannot find the paper you are looking for? You can Submit a new open access paper.