2 code implementations • 10 Sep 2023 • Gaurav Kumar Nayak, Inder Khatri, Shubham Randive, Ruchit Rawal, Anirban Chakraborty
With the increasing deployment of deep neural networks in safety-critical applications such as self-driving cars, medical imaging, anomaly detection, etc., adversarial robustness has become a crucial concern in the reliability of these networks in real-world scenarios.
1 code implementation • 12 Jan 2023 • Arjun Choudhry, Inder Khatri, Pankaj Gupta, Aaryan Gupta, Maxime Nicol, Marie-Jean Meurs, Dinesh Kumar Vishwakarma
We propose a Transformer-based NER approach for French, using adversarial adaptation to similar domain or general corpora to improve feature extraction and enable better generalization.
1 code implementation • 5 Dec 2022 • Arjun Choudhry, Pankaj Gupta, Inder Khatri, Aaryan Gupta, Maxime Nicol, Marie-Jean Meurs, Dinesh Kumar Vishwakarma
Named Entity Recognition (NER) involves the identification and classification of named entities in unstructured text into predefined classes.
no code implementations • 26 Nov 2022 • Arkajyoti Chakraborty, Inder Khatri, Arjun Choudhry, Pankaj Gupta, Dinesh Kumar Vishwakarma, Mukesh Prasad
Recent works on fake news detection have shown the efficacy of using emotions as a feature for improved performance.
no code implementations • 24 Nov 2022 • Arjun Choudhry, Inder Khatri, Arkajyoti Chakraborty, Dinesh Kumar Vishwakarma, Mukesh Prasad
Recent works on fake news detection have shown the efficacy of using emotions as a feature or emotions-based features for improved performance.
no code implementations • 22 Nov 2022 • Arjun Choudhry, Inder Khatri, Minni Jain, Dinesh Kumar Vishwakarma
We further analyze the performance of our multi-task approach for fake news detection in cross-domain settings to verify its efficacy for better generalization across datasets, and to verify that emotions act as a domain-independent feature.
no code implementations • 17 Nov 2022 • Aaryan Gupta, Inder Khatri, Arjun Choudhry, Pranav Chandhok, Dinesh Kumar Vishwakarma, Mukesh Prasad
In this work, we propose a community structures-based approach, which employs a K-Shell algorithm in order to generate a score for the connections between seed nodes and communities for low-budget scenarios.
1 code implementation • 3 Nov 2022 • Gaurav Kumar Nayak, Ruchit Rawal, Inder Khatri, Anirban Chakraborty
These methods rely on the generation of adversarial samples in every episode of training, which further adds a computational burden.
1 code implementation • 3 Nov 2022 • Gaurav Kumar Nayak, Inder Khatri, Ruchit Rawal, Anirban Chakraborty
At test time, WNR combined with trained regenerator network is prepended to the black box network, resulting in a high boost in adversarial accuracy.