Can Unsupervised Knowledge Transfer from Social Discussions Help Argument Mining?

1 code implementation • ACL 2022 • Subhabrata Dutta, Jeevesh Juneja, Dipankar Das, Tanmoy Chakraborty

Identifying argument components from unstructured texts and predicting the relationships expressed among them are two primary steps of argument mining.

Argument Mining Language Modelling +2

Finding patterns in Knowledge Attribution for Transformers

no code implementations • 3 May 2022 • Jeevesh Juneja, Ritu Agarwal

We analyze the Knowledge Neurons framework for the attribution of factual and relational knowledge to particular neurons in the transformer network.

Linear Connectivity Reveals Generalization Strategies

1 code implementation • 24 May 2022 • Jeevesh Juneja, Rachit Bansal, Kyunghyun Cho, João Sedoc, Naomi Saphra

It is widely accepted in the mode connectivity literature that when two neural networks are trained similarly on the same data, they are connected by a path through parameter space over which test set accuracy is maintained.

CoLA QQP +1