Search Results for author: Adarsh Kumar

Found 13 papers, 8 papers with code

Adversities are all you need: Classification of self-reported breast cancer posts on Twitter using Adversarial Fine-tuning

no code implementations NAACL (SMM4H) 2021 Adarsh Kumar, Ojasv Kamal, Susmita Mazumdar

In this paper, we describe our system entry for Shared Task 8 at SMM4H-2021, which is on automatic classification of self-reported breast cancer posts on Twitter.

Language Modelling

CounterGeDi: A controllable approach to generate polite, detoxified and emotional counterspeech

1 code implementation9 May 2022 Punyajoy Saha, Kanishk Singh, Adarsh Kumar, Binny Mathew, Animesh Mukherjee

We generate counterspeech using three datasets and observe significant improvement across different attribute scores.

Doing More by Doing Less: How Structured Partial Backpropagation Improves Deep Learning Clusters

1 code implementation20 Nov 2021 Adarsh Kumar, Kausik Subramanian, Shivaram Venkataraman, Aditya Akella

This simultaneously reduces network bandwidth, compute utilization, and memory footprint while preserving model quality.

DadaGP: A Dataset of Tokenized GuitarPro Songs for Sequence Models

1 code implementation30 Jul 2021 Pedro Sarmento, Adarsh Kumar, CJ Carr, Zack Zukowski, Mathieu Barthet, Yi-Hsuan Yang

In this work, we present DadaGP, a new symbolic music dataset comprising 26, 181 song scores in the GuitarPro format covering 739 musical genres, along with an accompanying tokenized format well-suited for generative sequence models such as the Transformer.

Genre classification Music Generation +2

Quantum Artificial Intelligence for the Science of Climate Change

1 code implementation28 Jul 2021 Manmeet Singh, Chirag Dhara, Adarsh Kumar, Sukhpal Singh Gill, Steve Uhlig

Climate change has become one of the biggest global problems increasingly compromising the Earth's habitability.

Team Phoenix at WASSA 2021: Emotion Analysis on News Stories with Pre-Trained Language Models

1 code implementation EACL (WASSA) 2021 Yash Butala, Kanishk Singh, Adarsh Kumar, Shrey Shrivastava

We describe our system entry for the WASSA 2021 Shared Task (for both Track-1 and Track-2), where we leveraged the information from Pre-trained language models for Track-specific Tasks.

Emotion Recognition

Accelerating Deep Learning Inference via Learned Caches

no code implementations18 Jan 2021 Arjun Balasubramanian, Adarsh Kumar, YuHan Liu, Han Cao, Shivaram Venkataraman, Aditya Akella

We present the design of GATI, an end-to-end prediction serving system that incorporates learned caches for low-latency DNN inference.

Hostility Detection in Hindi leveraging Pre-Trained Language Models

1 code implementation14 Jan 2021 Ojasv Kamal, Adarsh Kumar, Tejas Vaidhya

This paper harnesses attention based pre-trained models fine-tuned on Hindi data with Hostile-Non hostile task as Auxiliary and fusing its features for further sub-tasks classification.

Fake News Detection Hate Speech Detection +1

Can Adversarial Weight Perturbations Inject Neural Backdoors?

1 code implementation4 Aug 2020 Siddhant Garg, Adarsh Kumar, Vibhor Goel, YIngyu Liang

We introduce adversarial perturbations in the model weights using a composite loss on the predictions of the original model and the desired trigger through projected gradient descent.

MA-DST: Multi-Attention Based Scalable Dialog State Tracking

no code implementations7 Feb 2020 Adarsh Kumar, Peter Ku, Anuj Kumar Goyal, Angeliki Metallinou, Dilek Hakkani-Tur

Task oriented dialog agents provide a natural language interface for users to complete their goal.

Accelerating Deep Learning Inference via Freezing

no code implementations7 Feb 2020 Adarsh Kumar, Arjun Balasubramanian, Shivaram Venkataraman, Aditya Akella

In this work, we observe that caching intermediate layer outputs can help us avoid running all the layers of a DNN for a sizeable fraction of inference requests.

Quantization

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