research
∙
05/23/2023
Sāmayik: A Benchmark and Dataset for English-Sanskrit Translation
Sanskrit is a low-resource language with a rich heritage. Digitized Sans...
share
research
∙
05/11/2023
INGENIOUS: Using Informative Data Subsets for Efficient Pre-Training of Large Language Models
A salient characteristic of large pre-trained language models (PTLMs) is...
research
∙
05/04/2023
When Do Neural Nets Outperform Boosted Trees on Tabular Data?
Tabular data is one of the most commonly used types of data in machine l...
research
∙
11/02/2022
Speeding up NAS with Adaptive Subset Selection
A majority of recent developments in neural architecture search (NAS) ha...
research
∙
10/30/2022
Partitioned Gradient Matching-based Data Subset Selection for Compute-Efficient Robust ASR Training
Training state-of-the-art ASR systems such as RNN-T often has a high ass...
research
∙
10/13/2022
DICTDIS: Dictionary Constrained Disambiguation for Improved NMT
Domain-specific neural machine translation (NMT) systems (e.g., in educa...
research
∙
10/04/2022
DIAGNOSE: Avoiding Out-of-distribution Data using Submodular Information Measures
Avoiding out-of-distribution (OOD) data is critical for training supervi...
research
∙
10/04/2022
CLINICAL: Targeted Active Learning for Imbalanced Medical Image Classification
Training deep learning models on medical datasets that perform well for ...
research
∙
03/31/2022
Investigating Modality Bias in Audio Visual Video Parsing
We focus on the audio-visual video parsing (AVVP) problem that involves ...
research
∙
03/15/2022
AUTOMATA: Gradient Based Data Subset Selection for Compute-Efficient Hyper-parameter Tuning
Deep neural networks have seen great success in recent years; however, t...
research
∙
03/10/2022
BASIL: Balanced Active Semi-supervised Learning for Class Imbalanced Datasets
Current semi-supervised learning (SSL) methods assume a balance between ...
research
∙
03/03/2022
UDAAN - Machine Learning based Post-Editing tool for Document Translation
We introduce UDAAN, an open-source post-editing tool that can reduce man...
research
∙
02/22/2022
Submodlib: A Submodular Optimization Library
Submodular functions are a special class of set functions which naturall...
research
∙
02/07/2022
ALM-KD: Knowledge Distillation with noisy labels via adaptive loss mixing
Knowledge distillation is a technique where the outputs of a pretrained ...
research
∙
02/02/2022
Error Correction in ASR using Sequence-to-Sequence Models
Post-editing in Automatic Speech Recognition (ASR) entails automatically...
research
∙
10/10/2021
Personalizing ASR with limited data using targeted subset selection
We study the task of personalizing ASR models to a target non-native spe...
research
∙
09/23/2021
Learning to Robustly Aggregate Labeling Functions for Semi-supervised Data Programming
A critical bottleneck in supervised machine learning is the need for lar...
research
∙
08/19/2021
Wisdom of (Binned) Crowds: A Bayesian Stratification Paradigm for Crowd Counting
Datasets for training crowd counting deep networks are typically heavy-t...
research
∙
08/01/2021
SPEAR : Semi-supervised Data Programming in Python
We present SPEAR, an open-source python library for data programming wit...
research
∙
06/23/2021
Training Data Subset Selection for Regression with Controlled Generalization Error
Data subset selection from a large number of training instances has been...
research
∙
06/02/2021
Automatic Speech Recognition in Sanskrit: A New Speech Corpus and Modelling Insights
Automatic speech recognition (ASR) in Sanskrit is interesting, owing to ...
research
∙
05/21/2021
Rule Augmented Unsupervised Constituency Parsing
Recently, unsupervised parsing of syntactic trees has gained considerabl...
research
∙
04/30/2021
Submodular Mutual Information for Targeted Data Subset Selection
With the rapid growth of data, it is becoming increasingly difficult to ...
research
∙
04/14/2021
A Weakly Supervised Model for Solving Math word Problems
Solving math word problems (MWPs) is an important and challenging proble...
research
∙
04/11/2021
Unsupervised Learning of Explainable Parse Trees for Improved Generalisation
Recursive neural networks (RvNN) have been shown useful for learning sen...
research
∙
03/09/2021
Select, Substitute, Search: A New Benchmark for Knowledge-Augmented Visual Question Answering
Multimodal IR, spanning text corpus, knowledge graph and images, called ...
research
∙
02/27/2021
PRISM: A Unified Framework of Parameterized Submodular Information Measures for Targeted Data Subset Selection and Summarization
With increasing data, techniques for finding smaller, yet effective subs...
research
∙
01/26/2021
How Good is a Video Summary? A New Benchmarking Dataset and Evaluation Framework Towards Realistic Video Summarization
Automatic video summarization is still an unsolved problem due to severa...
research
∙
01/25/2021
Meta-Learning for Effective Multi-task and Multilingual Modelling
Natural language processing (NLP) tasks (e.g. question-answering in Engl...
research
∙
01/13/2021
Joint Learning of Hyperbolic Label Embeddings for Hierarchical Multi-label Classification
We consider the problem of multi-label classification where the labels l...
research
∙
12/19/2020
GLISTER: Generalization based Data Subset Selection for Efficient and Robust Learning
Large scale machine learning and deep models are extremely data-hungry. ...
research
∙
12/17/2020
LIGHTEN: Learning Interactions with Graph and Hierarchical TEmporal Networks for HOI in videos
Analyzing the interactions between humans and objects from a video inclu...
research
∙
10/12/2020
A Unified Framework for Generic, Query-Focused, Privacy Preserving and Update Summarization using Submodular Information Measures
We study submodular information measures as a rich framework for generic...
research
∙
08/22/2020
Data Programming using Semi-Supervision and Subset Selection
The paradigm of data programming <cit.> has shown a lot of promise in us...
research
∙
07/29/2020
Realistic Video Summarization through VISIOCITY: A New Benchmark and Evaluation Framework
Automatic video summarization is still an unsolved problem due to severa...
research
∙
11/22/2019
Data Programming using Continuous and Quality-Guided Labeling Functions
Scarcity of labeled data is a bottleneck for supervised learning models....
research
∙
11/08/2019
Question Generation from Paragraphs: A Tale of Two Hierarchical Models
Automatic question generation from paragraphs is an important and challe...
research
∙
09/24/2019
Multi-Person 3D Human Pose Estimation from Monocular Images
Multi-person 3D human pose estimation from a single image is a challengi...
research
∙
09/04/2019
ParaQG: A System for Generating Questions and Answers from Paragraphs
Generating syntactically and semantically valid and relevant questions f...
research
∙
08/19/2019
Tale of tails using rule augmented sequence labeling for event extraction
The problem of event extraction is a relatively difficult task for low r...
research
∙
06/06/2019
Cross-Lingual Training for Automatic Question Generation
Automatic question generation (QG) is a challenging problem in natural l...
research
∙
01/03/2019
Learning From Less Data: A Unified Data Subset Selection and Active Learning Framework for Computer Vision
Supervised machine learning based state-of-the-art computer vision techn...
research
∙
01/03/2019
Demystifying Multi-Faceted Video Summarization: Tradeoff Between Diversity,Representation, Coverage and Importance
This paper addresses automatic summarization of videos in a unified mann...
research
∙
09/24/2018
A Framework towards Domain Specific Video Summarization
In the light of exponentially increasing video content, video summarizat...
research
∙
08/15/2018
A framework for automatic question generation from text using deep reinforcement learning
Automatic question generation (QG) is a useful yet challenging task in N...
research
∙
05/28/2018
Learning From Less Data: Diversified Subset Selection and Active Learning in Image Classification Tasks
Supervised machine learning based state-of-the-art computer vision techn...
research
∙
03/07/2018
Automating Reading Comprehension by Generating Question and Answer Pairs
Neural network-based methods represent the state-of-the-art in question ...
research
∙
04/04/2017
