Search Results for author: Ganesh Ramakrishnan

Found 84 papers, 34 papers with code

WARM: A Weakly (+Semi) Supervised Math Word Problem Solver

1 code implementation COLING 2022 Oishik Chatterjee, Isha Pandey, Aashish Waikar, Vishwajeet Kumar, Ganesh Ramakrishnan

In order to address this challenge of equation annotation, we propose a weakly supervised model for solving MWPs by requiring only the final answer as supervision.

Math

LexGen: Domain-aware Multilingual Lexicon Generation

no code implementations18 May 2024 Karthika NJ, Ayush Maheshwari, Atul Kumar Singh, Preethi Jyothi, Ganesh Ramakrishnan, Krishnakant Bhatt

Owing to the research gap in lexicon generation, especially with a limited focus on the domain-specific area, we propose a new model to generate dictionary words for 6 Indian languages in the multi-domain setting.

SMART: Submodular Data Mixture Strategy for Instruction Tuning

1 code implementation13 Mar 2024 H S V N S Kowndinya Renduchintala, Sumit Bhatia, Ganesh Ramakrishnan

Instruction Tuning involves finetuning a language model on a collection of instruction-formatted datasets in order to enhance the generalizability of the model to unseen tasks.

Language Modelling

FAIR: Filtering of Automatically Induced Rules

no code implementations23 Feb 2024 Divya Jyoti Bajpai, Ayush Maheshwari, Manjesh Kumar Hanawal, Ganesh Ramakrishnan

The availability of large annotated data can be a critical bottleneck in training machine learning algorithms successfully, especially when applied to diverse domains.

text-classification Text Classification

INSITE: labelling medical images using submodular functions and semi-supervised data programming

no code implementations11 Feb 2024 Akshat Gautam, Anurag Shandilya, Akshit Srivastava, Venkatapathy Subramanian, Ganesh Ramakrishnan, Kshitij Jadhav

We demonstrate that informed subset selection followed by semi-supervised data programming methods using these images as exemplars perform better than other state-of-the-art semi-supervised methods.

Gradient Coreset for Federated Learning

1 code implementation13 Jan 2024 Durga Sivasubramanian, Lokesh Nagalapatti, Rishabh Iyer, Ganesh Ramakrishnan

We conduct experiments using four real-world datasets and show that GCFL is (1) more compute and energy efficient than FL, (2) robust to various kinds of noise in both the feature space and labels, (3) preserves the privacy of the validation dataset, and (4) introduces a small communication overhead but achieves significant gains in performance, particularly in cases when the clients' data is noisy.

Federated Learning

EIGEN: Expert-Informed Joint Learning Aggregation for High-Fidelity Information Extraction from Document Images

1 code implementation23 Nov 2023 Abhishek Singh, Venkatapathy Subramanian, Ayush Maheshwari, Pradeep Narayan, Devi Prasad Shetty, Ganesh Ramakrishnan

We empirically show that our EIGEN framework can significantly improve the performance of state-of-the-art deep models with the availability of very few labeled data instances.

Using Early Readouts to Mediate Featural Bias in Distillation

no code implementations28 Oct 2023 Rishabh Tiwari, Durga Sivasubramanian, Anmol Mekala, Ganesh Ramakrishnan, Pradeep Shenoy

Deep networks tend to learn spurious feature-label correlations in real-world supervised learning tasks.

Fairness

Sāmayik: A Benchmark and Dataset for English-Sanskrit Translation

1 code implementation23 May 2023 Ayush Maheshwari, Ashim Gupta, Amrith Krishna, Atul Kumar Singh, Ganesh Ramakrishnan, G. Anil Kumar, Jitin Singla

Translation models trained on our dataset demonstrate statistically significant improvements when translating out-of-domain contemporary corpora, outperforming models trained on older classical-era poetry datasets.

Machine Translation Translation

INGENIOUS: Using Informative Data Subsets for Efficient Pre-Training of Language Models

no code implementations11 May 2023 H S V N S Kowndinya Renduchintala, KrishnaTeja Killamsetty, Sumit Bhatia, Milan Aggarwal, Ganesh Ramakrishnan, Rishabh Iyer, Balaji Krishnamurthy

A salient characteristic of pre-trained language models (PTLMs) is a remarkable improvement in their generalization capability and emergence of new capabilities with increasing model capacity and pre-training dataset size.

When Do Neural Nets Outperform Boosted Trees on Tabular Data?

2 code implementations NeurIPS 2023 Duncan McElfresh, Sujay Khandagale, Jonathan Valverde, Vishak Prasad C, Benjamin Feuer, Chinmay Hegde, Ganesh Ramakrishnan, Micah Goldblum, Colin White

To this end, we conduct the largest tabular data analysis to date, comparing 19 algorithms across 176 datasets, and we find that the 'NN vs. GBDT' debate is overemphasized: for a surprisingly high number of datasets, either the performance difference between GBDTs and NNs is negligible, or light hyperparameter tuning on a GBDT is more important than choosing between NNs and GBDTs.

A Benchmark and Dataset for Post-OCR text correction in Sanskrit

1 code implementation15 Nov 2022 Ayush Maheshwari, Nikhil Singh, Amrith Krishna, Ganesh Ramakrishnan

Keeping this in mind, we release a multi-domain dataset, from areas as diverse as astronomy, medicine and mathematics, with some of them as old as 18 centuries.

Astronomy Optical Character Recognition (OCR)

Speeding up NAS with Adaptive Subset Selection

no code implementations2 Nov 2022 Vishak Prasad C, Colin White, Paarth Jain, Sibasis Nayak, Ganesh Ramakrishnan

A majority of recent developments in neural architecture search (NAS) have been aimed at decreasing the computational cost of various techniques without affecting their final performance.

Neural Architecture Search

Partitioned Gradient Matching-based Data Subset Selection for Compute-Efficient Robust ASR Training

no code implementations30 Oct 2022 Ashish Mittal, Durga Sivasubramanian, Rishabh Iyer, Preethi Jyothi, Ganesh Ramakrishnan

Training state-of-the-art ASR systems such as RNN-T often has a high associated financial and environmental cost.

DICTDIS: Dictionary Constrained Disambiguation for Improved NMT

no code implementations13 Oct 2022 Ayush Maheshwari, Piyush Sharma, Preethi Jyothi, Ganesh Ramakrishnan

In this work we present \dictdis, a lexically constrained NMT system that disambiguates between multiple candidate translations derived from dictionaries.

Machine Translation NMT

AutoML for Climate Change: A Call to Action

1 code implementation7 Oct 2022 Renbo Tu, Nicholas Roberts, Vishak Prasad, Sibasis Nayak, Paarth Jain, Frederic Sala, Ganesh Ramakrishnan, Ameet Talwalkar, Willie Neiswanger, Colin White

The challenge that climate change poses to humanity has spurred a rapidly developing field of artificial intelligence research focused on climate change applications.

AutoML

DIAGNOSE: Avoiding Out-of-distribution Data using Submodular Information Measures

no code implementations4 Oct 2022 Suraj Kothawade, Akshit Srivastava, Venkat Iyer, Ganesh Ramakrishnan, Rishabh Iyer

Avoiding out-of-distribution (OOD) data is critical for training supervised machine learning models in the medical imaging domain.

Active Learning

CLINICAL: Targeted Active Learning for Imbalanced Medical Image Classification

no code implementations4 Oct 2022 Suraj Kothawade, Atharv Savarkar, Venkat Iyer, Lakshman Tamil, Ganesh Ramakrishnan, Rishabh Iyer

It is often the case that a suboptimal performance is obtained on some classes due to the natural class imbalance issue that comes with medical data.

Active Learning Image Classification +1

Investigating Modality Bias in Audio Visual Video Parsing

no code implementations31 Mar 2022 Piyush Singh Pasi, Shubham Nemani, Preethi Jyothi, Ganesh Ramakrishnan

We focus on the audio-visual video parsing (AVVP) problem that involves detecting audio and visual event labels with temporal boundaries.

AUTOMATA: Gradient Based Data Subset Selection for Compute-Efficient Hyper-parameter Tuning

1 code implementation15 Mar 2022 KrishnaTeja Killamsetty, Guttu Sai Abhishek, Aakriti, Alexandre V. Evfimievski, Lucian Popa, Ganesh Ramakrishnan, Rishabh Iyer

Our central insight is that using an informative subset of the dataset for model training runs involved in hyper-parameter optimization, allows us to find the optimal hyper-parameter configuration significantly faster.

BASIL: Balanced Active Semi-supervised Learning for Class Imbalanced Datasets

no code implementations10 Mar 2022 Suraj Kothawade, Pavan Kumar Reddy, Ganesh Ramakrishnan, Rishabh Iyer

This issue is further pronounced in SSL methods, as they would use this biased model to obtain psuedo-labels (on the unlabeled data) during training.

Active Learning

UDAAN: Machine Learning based Post-Editing tool for Document Translation

1 code implementation3 Mar 2022 Ayush Maheshwari, Ajay Ravindran, Venkatapathy Subramanian, Ganesh Ramakrishnan

UDAAN has an end-to-end Machine Translation (MT) plus post-editing pipeline wherein users can upload a document to obtain raw MT output.

BIG-bench Machine Learning Document Translation +3

Submodlib: A Submodular Optimization Library

1 code implementation22 Feb 2022 Vishal Kaushal, Ganesh Ramakrishnan, Rishabh Iyer

A recent work has also leveraged submodular functions to propose submodular information measures which have been found to be very useful in solving the problems of guided subset selection and guided summarization.

Data Summarization

Adaptive Mixing of Auxiliary Losses in Supervised Learning

1 code implementation7 Feb 2022 Durga Sivasubramanian, Ayush Maheshwari, Pradeep Shenoy, Prathosh AP, Ganesh Ramakrishnan

In several supervised learning scenarios, auxiliary losses are used in order to introduce additional information or constraints into the supervised learning objective.

Denoising Knowledge Distillation +1

Error Correction in ASR using Sequence-to-Sequence Models

no code implementations2 Feb 2022 Samrat Dutta, Shreyansh Jain, Ayush Maheshwari, Souvik Pal, Ganesh Ramakrishnan, Preethi Jyothi

Post-editing in Automatic Speech Recognition (ASR) entails automatically correcting common and systematic errors produced by the ASR system.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

DITTO: Data-efficient and Fair Targeted Subset Selection for ASR Accent Adaptation

no code implementations10 Oct 2021 Suraj Kothawade, Anmol Mekala, Chandra Sekhara D, Mayank Kothyari, Rishabh Iyer, Ganesh Ramakrishnan, Preethi Jyothi

To address this problem, we propose DITTO (Data-efficient and faIr Targeted subseT selectiOn) that uses Submodular Mutual Information (SMI) functions as acquisition functions to find the most informative set of utterances matching a target accent within a fixed budget.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Wisdom of (Binned) Crowds: A Bayesian Stratification Paradigm for Crowd Counting

1 code implementation19 Aug 2021 Sravya Vardhani Shivapuja, Mansi Pradeep Khamkar, Divij Bajaj, Ganesh Ramakrishnan, Ravi Kiran Sarvadevabhatla

We analyze the performance of representative crowd counting approaches across standard datasets at per strata level and in aggregate.

Crowd Counting

SPEAR : Semi-supervised Data Programming in Python

1 code implementation1 Aug 2021 Guttu Sai Abhishek, Harshad Ingole, Parth Laturia, Vineeth Dorna, Ayush Maheshwari, Rishabh Iyer, Ganesh Ramakrishnan

SPEAR facilitates weak supervision in the form of heuristics (or rules) and association of noisy labels to the training dataset.

text-classification Text Classification

Training Data Subset Selection for Regression with Controlled Generalization Error

1 code implementation23 Jun 2021 Durga Sivasubramanian, Rishabh Iyer, Ganesh Ramakrishnan, Abir De

First, we represent this problem with simplified constraints using the dual of the original training problem and show that the objective of this new representation is a monotone and alpha-submodular function, for a wide variety of modeling choices.

regression

Effective Evaluation of Deep Active Learning on Image Classification Tasks

no code implementations16 Jun 2021 Nathan Beck, Durga Sivasubramanian, Apurva Dani, Ganesh Ramakrishnan, Rishabh Iyer

Issues in the current literature include sometimes contradictory observations on the performance of different AL algorithms, unintended exclusion of important generalization approaches such as data augmentation and SGD for optimization, a lack of study of evaluation facets like the labeling efficiency of AL, and little or no clarity on the scenarios in which AL outperforms random sampling (RS).

Active Learning Benchmarking +3

Submodular Mutual Information for Targeted Data Subset Selection

no code implementations30 Apr 2021 Suraj Kothawade, Vishal Kaushal, Ganesh Ramakrishnan, Jeff Bilmes, Rishabh Iyer

With the rapid growth of data, it is becoming increasingly difficult to train or improve deep learning models with the right subset of data.

Active Learning Image Classification

WARM: A Weakly (+Semi) Supervised Model for Solving Math word Problems

no code implementations14 Apr 2021 Oishik Chatterjee, Isha Pandey, Aashish Waikar, Vishwajeet Kumar, Ganesh Ramakrishnan

We approach this problem by first learning to generate the equation using the problem description and the final answer, which we subsequently use to train a supervised MWP solver.

Math

Cross-Modal learning for Audio-Visual Video Parsing

1 code implementation3 Apr 2021 Jatin Lamba, abhishek, Jayaprakash Akula, Rishabh Dabral, Preethi Jyothi, Ganesh Ramakrishnan

In this paper, we present a novel approach to the audio-visual video parsing (AVVP) task that demarcates events from a video separately for audio and visual modalities.

Event Detection Multiple Instance Learning +1

Rudder: A Cross Lingual Video and Text Retrieval Dataset

1 code implementation9 Mar 2021 Jayaprakash A, abhishek, Rishabh Dabral, Ganesh Ramakrishnan, Preethi Jyothi

Video retrieval using natural language queries requires learning semantically meaningful joint embeddings between the text and the audio-visual input.

Natural Language Queries Retrieval +2

PRISM: A Rich Class of Parameterized Submodular Information Measures for Guided Subset Selection

1 code implementation27 Feb 2021 Suraj Kothawade, Vishal Kaushal, Ganesh Ramakrishnan, Jeff Bilmes, Rishabh Iyer

Examples of such problems include: i)targeted learning, where the goal is to find subsets with rare classes or rare attributes on which the model is underperforming, and ii)guided summarization, where data (e. g., image collection, text, document or video) is summarized for quicker human consumption with specific additional user intent.

Image Classification

GRAD-MATCH: Gradient Matching based Data Subset Selection for Efficient Deep Model Training

3 code implementations27 Feb 2021 KrishnaTeja Killamsetty, Durga Sivasubramanian, Ganesh Ramakrishnan, Abir De, Rishabh Iyer

We show rigorous theoretical and convergence guarantees of the proposed algorithm and, through our extensive experiments on real-world datasets, show the effectiveness of our proposed framework.

Joint Learning of Hyperbolic Label Embeddings for Hierarchical Multi-label Classification

1 code implementation EACL 2021 Soumya Chatterjee, Ayush Maheshwari, Ganesh Ramakrishnan, Saketha Nath Jagaralpudi

Such a joint learning is expected to provide a twofold advantage: i) the classifier generalizes better as it leverages the prior knowledge of existence of a hierarchy over the labels, and ii) in addition to the label co-occurrence information, the label-embedding may benefit from the manifold structure of the input datapoints, leading to embeddings that are more faithful to the label hierarchy.

General Classification Hierarchical Multi-label Classification +1

GLISTER: Generalization based Data Subset Selection for Efficient and Robust Learning

1 code implementation19 Dec 2020 KrishnaTeja Killamsetty, Durga Sivasubramanian, Ganesh Ramakrishnan, Rishabh Iyer

Finally, we propose Glister-Active, an extension to batch active learning, and we empirically demonstrate the performance of Glister on a wide range of tasks including, (a) data selection to reduce training time, (b) robust learning under label noise and imbalance settings, and (c) batch-active learning with several deep and shallow models.

Active Learning

LIGHTEN: Learning Interactions with Graph and Hierarchical TEmporal Networks for HOI in videos

1 code implementation17 Dec 2020 Sai Praneeth Reddy Sunkesula, Rishabh Dabral, Ganesh Ramakrishnan

Analyzing the interactions between humans and objects from a video includes identification of the relationships between humans and the objects present in the video.

Human-Object Interaction Detection Relationship Detection +1

Semi-Supervised Data Programming with Subset Selection

1 code implementation Findings (ACL) 2021 Ayush Maheshwari, Oishik Chatterjee, KrishnaTeja Killamsetty, Ganesh Ramakrishnan, Rishabh Iyer

The first contribution of this work is an introduction of a framework, \model which is a semi-supervised data programming paradigm that learns a \emph{joint model} that effectively uses the rules/labelling functions along with semi-supervised loss functions on the feature space.

text-classification Text Classification

Realistic Video Summarization through VISIOCITY: A New Benchmark and Evaluation Framework

no code implementations29 Jul 2020 Vishal Kaushal, Suraj Kothawade, Rishabh Iyer, Ganesh Ramakrishnan

Thirdly, we demonstrate that in the presence of multiple ground truth summaries (due to the highly subjective nature of the task), learning from a single combined ground truth summary using a single loss function is not a good idea.

Benchmarking Video Summarization

Question Generation from Paragraphs: A Tale of Two Hierarchical Models

no code implementations8 Nov 2019 Vishwajeet Kumar, Raktim Chaki, Sai Teja Talluri, Ganesh Ramakrishnan, Yuan-Fang Li, Gholamreza Haffari

Specifically, we propose (a) a novel hierarchical BiLSTM model with selective attention and (b) a novel hierarchical Transformer architecture, both of which learn hierarchical representations of paragraphs.

Question Generation Question-Generation +2

Putting the Horse before the Cart: A Generator-Evaluator Framework for Question Generation from Text

no code implementations CONLL 2019 Vishwajeet Kumar, Ganesh Ramakrishnan, Yuan-Fang Li

The \textit{generator} is a sequence-to-sequence model that incorporates the \textit{structure} and \textit{semantics} of the question being generated.

Question Generation Question-Generation

Tale of tails using rule augmented sequence labeling for event extraction

no code implementations19 Aug 2019 Ayush Maheshwari, Hrishikesh Patel, Nandan Rathod, Ritesh Kumar, Ganesh Ramakrishnan, Pushpak Bhattacharyya

The problem of event extraction is a relatively difficult task for low resource languages due to the non-availability of sufficient annotated data.

Event Extraction

Putting the Horse Before the Cart:A Generator-Evaluator Framework for Question Generation from Text

no code implementations15 Aug 2018 Vishwajeet Kumar, Ganesh Ramakrishnan, Yuan-Fang Li

The {\it generator} is a sequence-to-sequence model that incorporates the {\it structure} and {\it semantics} of the question being generated.

Question Generation Question-Generation

Entity Resolution and Location Disambiguation in the Ancient Hindu Temples Domain using Web Data

no code implementations NAACL 2018 Ayush Maheshwari, Vishwajeet Kumar, Ganesh Ramakrishnan, J. Saketha Nath

We present a system for resolving entities and disambiguating locations based on publicly available web data in the domain of ancient Hindu Temples.

Clustering Entity Resolution

Learning From Less Data: Diversified Subset Selection and Active Learning in Image Classification Tasks

no code implementations28 May 2018 Vishal Kaushal, Anurag Sahoo, Khoshrav Doctor, Narasimha Raju, Suyash Shetty, Pankaj Singh, Rishabh Iyer, Ganesh Ramakrishnan

Supervised machine learning based state-of-the-art computer vision techniques are in general data hungry and pose the challenges of not having adequate computing resources and of high costs involved in human labeling efforts.

Active Learning BIG-bench Machine Learning +4

Learning Discriminative Relational Features for Sequence Labeling

no code implementations7 May 2017 Naveen Nair, Ajay Nagesh, Ganesh Ramakrishnan

For learning features derived from inputs at a particular sequence position, we propose a Hierarchical Kernels-based approach (referred to as Hierarchical Kernel Learning for Structured Output Spaces - StructHKL).

A Unified Multi-Faceted Video Summarization System

no code implementations4 Apr 2017 Anurag Sahoo, Vishal Kaushal, Khoshrav Doctor, Suyash Shetty, Rishabh Iyer, Ganesh Ramakrishnan

Most importantly, we also show that we can summarize hours of video data in a few seconds, and our system allows the user to generate summaries of various lengths and types interactively on the fly.

Extractive Summarization Query-focused Summarization +1

Efficient Reuse of Structured and Unstructured Resources for Ontology Population

no code implementations LREC 2014 Chetana Gavankar, Ashish Kulkarni, Ganesh Ramakrishnan

A domain ontology for an organization, often consists of classes whose instances are either specific to, or independent of the organization.

Information Retrieval Retrieval +1

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