Search Results for author: Shashank Gupta

Found 15 papers, 3 papers with code

Sparsely Activated Mixture-of-Experts are Robust Multi-Task Learners

no code implementations16 Apr 2022 Shashank Gupta, Subhabrata Mukherjee, Krishan Subudhi, Eduardo Gonzalez, Damien Jose, Ahmed H. Awadallah, Jianfeng Gao

Traditional multi-task learning (MTL) methods use dense networks that use the same set of shared weights across several different tasks.

Multi-Task Learning

Knowledge Infused Decoding

1 code implementation ICLR 2022 Ruibo Liu, Guoqing Zheng, Shashank Gupta, Radhika Gaonkar, Chongyang Gao, Soroush Vosoughi, Milad Shokouhi, Ahmed Hassan Awadallah

Hence, they tend to suffer from counterfactual or hallucinatory generation when used in knowledge-intensive natural language generation (NLG) tasks.

Text Generation

Exploring Low-Cost Transformer Model Compression for Large-Scale Commercial Reply Suggestions

no code implementations27 Nov 2021 Vaishnavi Shrivastava, Radhika Gaonkar, Shashank Gupta, Abhishek Jha

Fine-tuning pre-trained language models improves the quality of commercial reply suggestion systems, but at the cost of unsustainable training times.

Model Compression

Performance of Dense Coding and Teleportation for Random States --Augmentation via Pre-processing

no code implementations10 Dec 2020 Rivu Gupta, Shashank Gupta, Shiladitya Mal, Aditi Sen De

The local pre-processing employed here is based on positive operator valued measurements along with classical communication and we show that unlike dense coding with two-qubit random states, senders' operations are always helpful to probabilistically enhance the capabilities of implementing dense coding as well as teleportation.

Quantum Physics

Feature Extraction Functions for Neural Logic Rule Learning

no code implementations14 Aug 2020 Shashank Gupta, Antonio Robles-Kelly, Mohamed Reda Bouadjenek

Combining symbolic human knowledge with neural networks provides a rule-based ante-hoc explanation of the output.

Sentiment Analysis

Genuine Einstein-Podolsky-Rosen steering of three-qubit states by multiple sequential observers

no code implementations7 Jul 2020 Shashank Gupta, Ananda G. Maity, Debarshi Das, Arup Roy, A. S. Majumdar

We investigate the possibility of multiple use of a single copy of three-qubit states for genuine tripartite Einstein-Podolsky-Rosen (EPR) steering.

Quantum Physics

On Application of Bayesian Parametric and Non-parametric Methods for User Cohorting in Product Search

no code implementations WS 2020 Shashank Gupta

To the best of our knowledge, this is the first work that presents a comparative study of various Bayesian clustering methods in the context of product search.

Semi-Supervised Recurrent Neural Network for Adverse Drug Reaction Mention Extraction

no code implementations6 Sep 2017 Shashank Gupta, Sachin Pawar, Nitin Ramrakhiyani, Girish Palshikar, Vasudeva Varma

Current methods in ADR mention extraction relies on supervised learning methods, which suffers from labeled data scarcity problem.

Deep Learning for Hate Speech Detection in Tweets

1 code implementation1 Jun 2017 Pinkesh Badjatiya, Shashank Gupta, Manish Gupta, Vasudeva Varma

Hate speech detection on Twitter is critical for applications like controversial event extraction, building AI chatterbots, content recommendation, and sentiment analysis.

Event Extraction Hate Speech Detection +2

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