Search Results for author: Neeraj Varshney

Found 17 papers, 3 papers with code

Can Open-Domain QA Reader Utilize External Knowledge Efficiently like Humans?

no code implementations23 Nov 2022 Neeraj Varshney, Man Luo, Chitta Baral

Comparing with the FiD reader, this approach matches its accuracy by utilizing just 18. 32% of its reader inference cost and also outperforms it by achieving up to 55. 10% accuracy on NQ Open.

TriviaQA

Performance Analysis of LEO Satellite-Based IoT Networks in the Presence of Interference

no code implementations8 Nov 2022 Ayush Kumar Dwivedi, Sachin Chaudhari, Neeraj Varshney, Pramod K. Varshney

Statistical characteristics of the range and the number of visible satellites are derived for a given mask angle.

"John is 50 years old, can his son be 65?" Evaluating NLP Models' Understanding of Feasibility

no code implementations14 Oct 2022 Himanshu Gupta, Neeraj Varshney, Swaroop Mishra, Kuntal Kumar Pal, Saurabh Arjun Sawant, Kevin Scaria, Siddharth Goyal, Chitta Baral

We introduce FeasibilityQA, a question-answering dataset involving binary classification (BCQ) and multi-choice multi-correct questions (MCQ) that test understanding of feasibility.

Question Answering

Model Cascading: Towards Jointly Improving Efficiency and Accuracy of NLP Systems

no code implementations11 Oct 2022 Neeraj Varshney, Chitta Baral

Through comprehensive experiments in multiple task settings that differ in the number of models available for cascading (K value), we show that cascading improves both the computational efficiency and the prediction accuracy.

Let the Model Decide its Curriculum for Multitask Learning

no code implementations DeepLo 2022 Neeraj Varshney, Swaroop Mishra, Chitta Baral

Curriculum learning strategies in prior multi-task learning approaches arrange datasets in a difficulty hierarchy either based on human perception or by exhaustively searching the optimal arrangement.

Multi-Task Learning

ILDAE: Instance-Level Difficulty Analysis of Evaluation Data

1 code implementation ACL 2022 Neeraj Varshney, Swaroop Mishra, Chitta Baral

Knowledge of questions' difficulty level helps a teacher in several ways, such as estimating students' potential quickly by asking carefully selected questions and improving quality of examination by modifying trivial and hard questions.

Unsupervised Natural Language Inference Using PHL Triplet Generation

1 code implementation Findings (ACL) 2022 Neeraj Varshney, Pratyay Banerjee, Tejas Gokhale, Chitta Baral

Transformer-based models achieve impressive performance on numerous Natural Language Inference (NLI) benchmarks when trained on respective training datasets.

Natural Language Inference

Hybrid Transceiver Design for Tera-Hertz MIMO Systems Relying on Bayesian Learning Aided Sparse Channel Estimation

no code implementations20 Sep 2021 Suraj Srivastava, Ajeet Tripathi, Neeraj Varshney, Aditya K. Jagannatham, Lajos Hanzo

Hybrid transceiver design in multiple-input multiple-output (MIMO) Tera-Hertz (THz) systems relying on sparse channel state information (CSI) estimation techniques is conceived.

Interviewer-Candidate Role Play: Towards Developing Real-World NLP Systems

no code implementations1 Jul 2021 Neeraj Varshney, Swaroop Mishra, Chitta Baral

However, our task leaves a significant challenge for NLP researchers to further improve OOD performance at each stage.

Natural Language Inference

On the Performance of the Primary and Secondary Links in a 3-D Underlay Cognitive Molecular Communication

no code implementations11 Feb 2021 Nithin V. Sabu, Neeraj Varshney, Abhishek K. Gupta

In this work, we consider a system in three-dimensional (3-D) space with two coexisting communication links, each between a point transmitter and fully-absorbing spherical receiver (FAR), where the one link (termed primary) has priority over the second link (termed secondary).

Information Theory Information Theory

Can Transformers Reason About Effects of Actions?

no code implementations17 Dec 2020 Pratyay Banerjee, Chitta Baral, Man Luo, Arindam Mitra, Kuntal Pal, Tran C. Son, Neeraj Varshney

A recent work has shown that transformers are able to "reason" with facts and rules in a limited setting where the rules are natural language expressions of conjunctions of conditions implying a conclusion.

Common Sense Reasoning Question Answering

Towards Improving Selective Prediction Ability of NLP Systems

no code implementations RepL4NLP (ACL) 2022 Neeraj Varshney, Swaroop Mishra, Chitta Baral

In (IID, OOD) settings, we show that the representations learned by our calibrator result in an improvement of (15. 81%, 5. 64%) and (6. 19%, 13. 9%) over 'MaxProb' -- a selective prediction baseline -- on NLI and DD tasks respectively.

Natural Language Inference

Beamformed Energy Detection in the Presence of an Interferer for Cognitive mmWave Network

no code implementations31 Jul 2020 Madhuri Latha Mannedu, Sai Krishna Charan Dara, Sachin Chaudhari, Neeraj Varshney

To demonstrate the bound on the system performance, the proposed sensing scheme is designed under the knowledge of full channel state information (CSI) at the SU for the PU-SU and Interferer-SU channels.

Towards Question Format Independent Numerical Reasoning: A Set of Prerequisite Tasks

no code implementations18 May 2020 Swaroop Mishra, Arindam Mitra, Neeraj Varshney, Bhavdeep Sachdeva, Chitta Baral

However, there exists a strong need for a benchmark which can evaluate the abilities of models, in performing question format independent numerical reasoning, as (i) the numerical reasoning capabilities we want to teach are not controlled by question formats, (ii) for numerical reasoning technology to have the best possible application, it must be able to process language and reason in a way that is not exclusive to a single format, task, dataset or domain.

Natural Language Inference Question Answering +1

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