Zobrazeno 1 - 10
of 35
pro vyhledávání: '"Bansal, Rachit"'
Autor:
Bansal, Rachit, Samanta, Bidisha, Dalmia, Siddharth, Gupta, Nitish, Vashishth, Shikhar, Ganapathy, Sriram, Bapna, Abhishek, Jain, Prateek, Talukdar, Partha
Foundational models with billions of parameters which have been trained on large corpora of data have demonstrated non-trivial skills in a variety of domains. However, due to their monolithic structure, it is challenging and expensive to augment them
Externí odkaz:
http://arxiv.org/abs/2401.02412
Neural networks are known to exploit spurious artifacts (or shortcuts) that co-occur with a target label, exhibiting heuristic memorization. On the other hand, networks have been shown to memorize training examples, resulting in example-level memoriz
Externí odkaz:
http://arxiv.org/abs/2210.09404
Large transformer-based pre-trained language models have achieved impressive performance on a variety of knowledge-intensive tasks and can capture factual knowledge in their parameters. We argue that storing large amounts of knowledge in the model pa
Externí odkaz:
http://arxiv.org/abs/2208.06458
Pre-trained Language Models (PTLMs) have been shown to perform well on natural language tasks. Many prior works have leveraged structured commonsense present in the form of entities linked through labeled relations in Knowledge Graphs (KGs) to assist
Externí odkaz:
http://arxiv.org/abs/2206.05706
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. Under some circumstances,
Externí odkaz:
http://arxiv.org/abs/2205.12411
Autor:
Bansal, Rachit, Choudhary, Himanshu, Punia, Ravneet, Schenk, Niko, Dahl, Jacob L, Pagé-Perron, Émilie
Despite the recent advancements of attention-based deep learning architectures across a majority of Natural Language Processing tasks, their application remains limited in a low-resource setting because of a lack of pre-trained models for such langua
Externí odkaz:
http://arxiv.org/abs/2105.14515
Fake tweets are observed to be ever-increasing, demanding immediate countermeasures to combat their spread. During COVID-19, tweets with misinformation should be flagged and neutralized in their early stages to mitigate the damages. Most of the exist
Externí odkaz:
http://arxiv.org/abs/2104.05321
Autor:
Paka, William Scott, Bansal, Rachit, Kaushik, Abhay, Sengupta, Shubhashis, Chakraborty, Tanmoy
As the COVID-19 pandemic sweeps across the world, it has been accompanied by a tsunami of fake news and misinformation on social media. At the time when reliable information is vital for public health and safety, COVID-19 related fake news has been s
Externí odkaz:
http://arxiv.org/abs/2102.08924
Autor:
Pruthi, Danish, Bansal, Rachit, Dhingra, Bhuwan, Soares, Livio Baldini, Collins, Michael, Lipton, Zachary C., Neubig, Graham, Cohen, William W.
While many methods purport to explain predictions by highlighting salient features, what aims these explanations serve and how they ought to be evaluated often go unstated. In this work, we introduce a framework to quantify the value of explanations
Externí odkaz:
http://arxiv.org/abs/2012.00893
Publikováno v:
In New BIOTECHNOLOGY 25 September 2019 52:9-18
