Search Results for author: Gaurav Kumar

Found 25 papers, 12 papers with code

TabPert : An Effective Platform for Tabular Perturbation

1 code implementation EMNLP (ACL) 2021 Nupur Jain, Vivek Gupta, Anshul Rai, Gaurav Kumar

To grasp the true reasoning ability, the Natural Language Inference model should be evaluated on counterfactual data.

counterfactual Natural Language Inference

Learning Curricula for Multilingual Neural Machine Translation Training

no code implementations MTSummit 2021 Gaurav Kumar, Philipp Koehn, Sanjeev Khudanpur

Low-resource Multilingual Neural Machine Translation (MNMT) is typically tasked with improving the translation performance on one or more language pairs with the aid of high-resource language pairs.

Machine Translation Translation

CFAT: Unleashing TriangularWindows for Image Super-resolution

1 code implementation24 Mar 2024 Abhisek Ray, Gaurav Kumar, Maheshkumar H. Kolekar

To overcome these weaknesses, we propose a non-overlapping triangular window technique that synchronously works with the rectangular one to mitigate boundary-level distortion and allows the model to access more unique sifting modes.

Image Super-Resolution

InterroGate: Learning to Share, Specialize, and Prune Representations for Multi-task Learning

no code implementations26 Feb 2024 Babak Ehteshami Bejnordi, Gaurav Kumar, Amelie Royer, Christos Louizos, Tijmen Blankevoort, Mohsen Ghafoorian

In this work, we propose \textit{InterroGate}, a novel multi-task learning (MTL) architecture designed to mitigate task interference while optimizing inference computational efficiency.

Computational Efficiency Multi-Task Learning

TabPert: An Effective Platform for Tabular Perturbation

1 code implementation2 Aug 2021 Nupur Jain, Vivek Gupta, Anshul Rai, Gaurav Kumar

To truly grasp reasoning ability, a Natural Language Inference model should be evaluated on counterfactual data.

counterfactual Natural Language Inference

Optimizing Data Augmentation Policy Through Random Unidimensional Search

1 code implementation16 Jun 2021 Xiaomeng Dong, Michael Potter, Gaurav Kumar, Yun-chan Tsai, V. Ratna Saripalli, Theodore Trafalis

It is no secret amongst deep learning researchers that finding the optimal data augmentation strategy during training can mean the difference between state-of-the-art performance and a run-of-the-mill result.

Data Augmentation

Learning Policies for Multilingual Training of Neural Machine Translation Systems

no code implementations11 Mar 2021 Gaurav Kumar, Philipp Koehn, Sanjeev Khudanpur

Low-resource Multilingual Neural Machine Translation (MNMT) is typically tasked with improving the translation performance on one or more language pairs with the aid of high-resource language pairs.

Machine Translation Translation

Learning Feature Weights using Reward Modeling for Denoising Parallel Corpora

no code implementations WMT (EMNLP) 2021 Gaurav Kumar, Philipp Koehn, Sanjeev Khudanpur

These feature weights which are optimized directly for the task of improving translation performance, are used to score and filter sentences in the noisy corpora more effectively.

Denoising Language Modelling +4

Role of corner flow separation in unsteady dynamics of hypersonic flow over a double wedge geometry

no code implementations10 Mar 2021 Gaurav Kumar, Ashoke De

The present work seeks out to investigate the origin of such oscillations in a low enthalpy hypersonic flow with different aft wedge angles and wedge length ratios. In the current study, viscous flow over a double wedge at Mach 7 and fore wedge angle of 30{\deg} is considered.

Fluid Dynamics

Solving Physics Puzzles by Reasoning about Paths

2 code implementations14 Nov 2020 Augustin Harter, Andrew Melnik, Gaurav Kumar, Dhruv Agarwal, Animesh Garg, Helge Ritter

We propose a new deep learning model for goal-driven tasks that require intuitive physical reasoning and intervention in the scene to achieve a desired end goal.

Object

AMUSED: A Multi-Stream Vector Representation Method for Use in Natural Dialogue

no code implementations LREC 2020 Gaurav Kumar, Rishabh Joshi, Jaspreet Singh, Promod Yenigalla

The problem of building a coherent and non-monotonous conversational agent with proper discourse and coverage is still an area of open research.

Retrieval Sentence +1

FastEstimator: A Deep Learning Library for Fast Prototyping and Productization

no code implementations7 Oct 2019 Xiaomeng Dong, Jun-Pyo Hong, Hsi-Ming Chang, Michael Potter, Aritra Chowdhury, Purujit Bahl, Vivek Soni, Yun-chan Tsai, Rajesh Tamada, Gaurav Kumar, Caroline Favart, V. Ratna Saripalli, Gopal Avinash

As the complexity of state-of-the-art deep learning models increases by the month, implementation, interpretation, and traceability become ever-more-burdensome challenges for AI practitioners around the world.

Phonon Lifetimes and Thermal Conductivity of the Molecular Crystal $α$-RDX

1 code implementation26 Apr 2019 Gaurav Kumar, Francis G. VanGessel, Daniel C. Elton, Peter W. Chung

This is likely because diffusive carriers contribute to over 95% of the thermal conductivity in ${\alpha}$-RDX.

Materials Science

A Phonon Boltzmann Study of Microscale Thermal Transport in $α$-RDX Cook-Off

1 code implementation24 Aug 2018 Francis G. VanGessel, Gaurav Kumar, Daniel C. Elton, Peter W. Chung

The microscale thermal transport properties of $\alpha$RDX are believed to be major factors in the initiation process.

Materials Science

Using of heterogeneous corpora for training of an ASR system

no code implementations1 Jun 2017 Jan Trmal, Gaurav Kumar, Vimal Manohar, Sanjeev Khudanpur, Matt Post, Paul McNamee

The paper summarizes the development of the LVCSR system built as a part of the Pashto speech-translation system at the SCALE (Summer Camp for Applied Language Exploration) 2015 workshop on "Speech-to-text-translation for low-resource languages".

speech-recognition Speech Recognition +2

DyNet: The Dynamic Neural Network Toolkit

4 code implementations15 Jan 2017 Graham Neubig, Chris Dyer, Yoav Goldberg, Austin Matthews, Waleed Ammar, Antonios Anastasopoulos, Miguel Ballesteros, David Chiang, Daniel Clothiaux, Trevor Cohn, Kevin Duh, Manaal Faruqui, Cynthia Gan, Dan Garrette, Yangfeng Ji, Lingpeng Kong, Adhiguna Kuncoro, Gaurav Kumar, Chaitanya Malaviya, Paul Michel, Yusuke Oda, Matthew Richardson, Naomi Saphra, Swabha Swayamdipta, Pengcheng Yin

In the static declaration strategy that is used in toolkits like Theano, CNTK, and TensorFlow, the user first defines a computation graph (a symbolic representation of the computation), and then examples are fed into an engine that executes this computation and computes its derivatives.

graph construction

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