Search Results for author: Siddharth Singh

Found 23 papers, 3 papers with code

The Impact of Automatic Pre-annotation in Clinical Note Data Element Extraction - the CLEAN Tool

no code implementations11 Aug 2018 Tsung-Ting Kuo, Jina Huh, Ji-Hoon Kim, Robert El-Kareh, Siddharth Singh, Stephanie Feudjio Feupe, Vincent Kuri, Gordon Lin, Michele E. Day, Lucila Ohno-Machado, Chun-Nan Hsu

Our study introduces CLEAN (CLinical note rEview and ANnotation), a pre-annotation-based cNLP annotation system to improve clinical note annotation of data elements, and comprehensively compares CLEAN with the widely-used annotation system Brat Rapid Annotation Tool (BRAT).

Open-Ended Question Answering

RoboNet: Large-Scale Multi-Robot Learning

no code implementations24 Oct 2019 Sudeep Dasari, Frederik Ebert, Stephen Tian, Suraj Nair, Bernadette Bucher, Karl Schmeckpeper, Siddharth Singh, Sergey Levine, Chelsea Finn

This leads to a frequent tension in robotic learning: how can we learn generalizable robotic controllers without having to collect impractically large amounts of data for each separate experiment?

Video Prediction

Developing a Multilingual Annotated Corpus of Misogyny and Aggression

no code implementations LREC 2020 Shiladitya Bhattacharya, Siddharth Singh, Ritesh Kumar, Akanksha Bansal, Akash Bhagat, Yogesh Dawer, Bornini Lahiri, Atul Kr. Ojha

In this paper, we discuss the development of a multilingual annotated corpus of misogyny and aggression in Indian English, Hindi, and Indian Bangla as part of a project on studying and automatically identifying misogyny and communalism on social media (the ComMA Project).

Stance Detection in Web and Social Media: A Comparative Study

1 code implementation12 Jul 2020 Shalmoli Ghosh, Prajwal Singhania, Siddharth Singh, Koustav Rudra, Saptarshi Ghosh

Online forums and social media platforms are increasingly being used to discuss topics of varying polarities where different people take different stances.

Stance Detection

Domain Adaptation for Real-World Single View 3D Reconstruction

no code implementations24 Aug 2021 Brandon Leung, Siddharth Singh, Arik Horodniceanu

Results are performed with ShapeNet as the source domain and domains within the Object Dataset Domain Suite (ODDS) dataset as the target, which is a real world multiview, multidomain image dataset.

3D Reconstruction Object Reconstruction +2

AxoNN: An asynchronous, message-driven parallel framework for extreme-scale deep learning

no code implementations25 Oct 2021 Siddharth Singh, Abhinav Bhatele

This has necessitated the development of efficient algorithms to train these neural networks in parallel on large-scale GPU-based clusters.

A Survey and Empirical Evaluation of Parallel Deep Learning Frameworks

no code implementations9 Nov 2021 Daniel Nichols, Siddharth Singh, Shu-Huai Lin, Abhinav Bhatele

This phenomenon has spurred the development of algorithms for distributed training of neural networks over a larger number of hardware accelerators.

The ComMA Dataset V0.2: Annotating Aggression and Bias in Multilingual Social Media Discourse

no code implementations LREC 2022 Ritesh Kumar, Enakshi Nandi, Laishram Niranjana Devi, Shyam Ratan, Siddharth Singh, Akash Bhagat, Yogesh Dawer

In this paper, we discuss the development of a multilingual dataset annotated with a hierarchical, fine-grained tagset marking different types of aggression and the "context" in which they occur.

Aggression Identification

Demo of the Linguistic Field Data Management and Analysis System -- LiFE

no code implementations22 Mar 2022 Siddharth Singh, Ritesh Kumar, Shyam Ratan, Sonal Sinha

The interface allows creation of multiple projects that could be shared with the other users.

Management

Annotated Speech Corpus for Low Resource Indian Languages: Awadhi, Bhojpuri, Braj and Magahi

no code implementations26 Jun 2022 Ritesh Kumar, Siddharth Singh, Shyam Ratan, Mohit Raj, Sonal Sinha, Bornini Lahiri, Vivek Seshadri, Kalika Bali, Atul Kr. Ojha

In this paper we discuss an in-progress work on the development of a speech corpus for four low-resource Indo-Aryan languages -- Awadhi, Bhojpuri, Braj and Magahi using the field methods of linguistic data collection.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Exploiting Sparsity in Pruned Neural Networks to Optimize Large Model Training

no code implementations10 Feb 2023 Siddharth Singh, Abhinav Bhatele

Parallel training of neural networks at scale is challenging due to significant overheads arising from communication.

A Hybrid Tensor-Expert-Data Parallelism Approach to Optimize Mixture-of-Experts Training

1 code implementation11 Mar 2023 Siddharth Singh, Olatunji Ruwase, Ammar Ahmad Awan, Samyam Rajbhandari, Yuxiong He, Abhinav Bhatele

Mixture-of-Experts (MoE) is a neural network architecture that adds sparsely activated expert blocks to a base model, increasing the number of parameters without impacting computational costs.

A 4D Hybrid Algorithm to Scale Parallel Training to Thousands of GPUs

no code implementations22 May 2023 Siddharth Singh, Prajwal Singhania, Aditya K. Ranjan, Zack Sating, Abhinav Bhatele

Large communication costs are a critical bottleneck in training state-of-the-art neural networks on distributed systems.

Jorge: Approximate Preconditioning for GPU-efficient Second-order Optimization

no code implementations18 Oct 2023 Siddharth Singh, Zachary Sating, Abhinav Bhatele

The primary efficiency bottleneck in such optimizers is matrix inverse calculations in the preconditioning step, which are expensive to compute on GPUs.

Computational Efficiency Second-order methods

A Framework for Realistic Simulation of Daily Human Activity

no code implementations26 Nov 2023 Ifrah Idrees, Siddharth Singh, Kerui Xu, Dylan F. Glas

For social robots like Astro which interact with and adapt to the daily movements of users within the home, realistic simulation of human activity is needed for feature development and testing.

HarmPot: An Annotation Framework for Evaluating Offline Harm Potential of Social Media Text

no code implementations17 Mar 2024 Ritesh Kumar, Ojaswee Bhalla, Madhu Vanthi, Shehlat Maknoon Wani, Siddharth Singh

In this paper, we discuss the development of an annotation schema to build datasets for evaluating the offline harm potential of social media texts.

Demo of the Linguistic Field Data Management and Analysis System - LiFE

no code implementations ICON 2021 Siddharth Singh, Ritesh Kumar, Shyam Ratan, Sonal Sinha

Since its a web-based application, it also allows for seamless collaboration among multiple persons and sharing the data, models, etc with each other.

Management

Towards a Unified Tool for the Management of Data and Technologies in Field Linguistics and Computational Linguistics - LiFE

no code implementations EURALI (LREC) 2022 Siddharth Singh, Ritesh Kumar, Shyam Ratan, Sonal Sinha

The tool provides a one-click interface to train NLP models for various tasks using the data stored in the system and then use it for assistance in further storage of the data (especially for the field linguists).

Management

ComMA@ICON: Multilingual Gender Biased and Communal Language Identification Task at ICON-2021

no code implementations ICON 2021 Ritesh Kumar, Shyam Ratan, Siddharth Singh, Enakshi Nandi, Laishram Niranjana Devi, Akash Bhagat, Yogesh Dawer, Bornini Lahiri, Akanksha Bansal

If approached as three separate classification tasks, the task includes three sub-tasks: aggression identification (sub-task A), gender bias identification (sub-task B), and communal bias identification (sub-task C).

Aggression Identification Classification +2

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