Mitesh M. Khapra

research

∙ 05/25/2023

IndicTrans2: Towards High-Quality and Accessible Machine Translation Models for all 22 Scheduled Indian Languages

India has a rich linguistic landscape with languages from 4 major langua...

0 AI4Bharat, et al. ∙

research

∙ 05/25/2023

Bhasha-Abhijnaanam: Native-script and romanized Language Identification for 22 Indic languages

We create publicly available language identification (LID) datasets and ...

0 Yash Madhani, et al. ∙

research

∙ 05/25/2023

Svarah: Evaluating English ASR Systems on Indian Accents

India is the second largest English-speaking country in the world with a...

0 Tahir Javed, et al. ∙

research

∙ 05/24/2023

Vistaar: Diverse Benchmarks and Training Sets for Indian Language ASR

Improving ASR systems is necessary to make new LLM-based use-cases acces...

0 Kaushal Santosh Bhogale, et al. ∙

research

∙ 05/12/2023

A Comprehensive Analysis of Adapter Efficiency

Adapters have been positioned as a parameter-efficient fine-tuning (PEFT...

0 Nandini Mundra, et al. ∙

research

∙ 12/20/2022

IndicMT Eval: A Dataset to Meta-Evaluate Machine Translation metrics for Indian Languages

The rapid growth of machine translation (MT) systems has necessitated co...

0 Ananya B. Sai, et al. ∙

research

∙ 12/20/2022

Naamapadam: A Large-Scale Named Entity Annotated Data for Indic Languages

We present, Naamapadam, the largest publicly available Named Entity Reco...

0 Arnav Mhaske, et al. ∙

research

∙ 12/11/2022

IndicXTREME: A Multi-Task Benchmark For Evaluating Indic Languages

In this work, we introduce IndicXTREME, a benchmark consisting of nine d...

0 Sumanth Doddapaneni, et al. ∙

research

∙ 11/17/2022

Towards Building Text-To-Speech Systems for the Next Billion Users

Deep learning based text-to-speech (TTS) systems have been evolving rapi...

0 Gokul Karthik Kumar, et al. ∙

research

∙ 08/26/2022

Effectiveness of Mining Audio and Text Pairs from Public Data for Improving ASR Systems for Low-Resource Languages

End-to-end (E2E) models have become the default choice for state-of-the-...

1 Kaushal Santosh Bhogale, et al. ∙

research

∙ 08/24/2022

IndicSUPERB: A Speech Processing Universal Performance Benchmark for Indian languages

A cornerstone in AI research has been the creation and adoption of stand...

0 Tahir Javed, et al. ∙

research

∙ 05/06/2022

Aksharantar: Towards building open transliteration tools for the next billion users

We introduce Aksharantar, the largest publicly available transliteration...

0 Yash Madhani, et al. ∙

research

∙ 03/26/2022

Joint Transformer/RNN Architecture for Gesture Typing in Indic Languages

Gesture typing is a method of typing words on a touch-based keyboard by ...

5 Emil Biju, et al. ∙

research

∙ 03/23/2022

Input-specific Attention Subnetworks for Adversarial Detection

Self-attention heads are characteristic of Transformer models and have b...

4 Emil Biju, et al. ∙

research

∙ 03/12/2022

A Survey in Adversarial Defences and Robustness in NLP

In recent years, it has been seen that deep neural networks are lacking ...

0 Shreya Goyal, et al. ∙

research

∙ 03/11/2022

Active Evaluation: Efficient NLG Evaluation with Few Pairwise Comparisons

Recent studies have shown the advantages of evaluating NLG systems using...

0 Akash Kumar Mohankumar, et al. ∙

research

∙ 11/06/2021

Towards Building ASR Systems for the Next Billion Users

Recent methods in speech and language technology pretrain very LARGE mod...

3 Tahir Javed, et al. ∙

research

∙ 10/09/2021

A Framework for Rationale Extraction for Deep QA models

As neural-network-based QA models become deeper and more complex, there ...

0 Sahana Ramnath, et al. ∙

research

∙ 09/26/2021

On the Prunability of Attention Heads in Multilingual BERT

Large multilingual models, such as mBERT, have shown promise in crosslin...

6 Aakriti Budhraja, et al. ∙

research

∙ 09/13/2021

Perturbation CheckLists for Evaluating NLG Evaluation Metrics

Natural Language Generation (NLG) evaluation is a multifaceted task requ...

5 Ananya B. Sai, et al. ∙

research

∙ 09/07/2021

IndicBART: A Pre-trained Model for Natural Language Generation of Indic Languages

In this paper we present IndicBART, a multilingual, sequence-to-sequence...

7 Raj Dabre, et al. ∙

research

∙ 07/01/2021

A Primer on Pretrained Multilingual Language Models

Multilingual Language Models (MLLMs) such as mBERT, XLM, XLM-R, etc. hav...

4 Sumanth Doddapaneni, et al. ∙

research

∙ 01/22/2021

The heads hypothesis: A unifying statistical approach towards understanding multi-headed attention in BERT

Multi-headed attention heads are a mainstay in transformer-based models....

5 Madhura Pande, et al. ∙

research

∙ 11/30/2020

Unsupervised Deep Video Denoising

Deep convolutional neural networks (CNNs) currently achieve state-of-the...

8 Dev Yashpal Sheth, et al. ∙

research

∙ 10/18/2020

Towards Interpreting BERT for Reading Comprehension Based QA

BERT and its variants have achieved state-of-the-art performance in vari...

0 Sahana Ramnath, et al. ∙

research

∙ 10/01/2020

Evaluating a Generative Adversarial Framework for Information Retrieval

Recent advances in Generative Adversarial Networks (GANs) have resulted ...

0 Ameet Deshpande, et al. ∙

research

∙ 09/23/2020

Improving Dialog Evaluation with a Multi-reference Adversarial Dataset and Large Scale Pretraining

There is an increasing focus on model-based dialog evaluation metrics su...

0 Ananya B. Sai, et al. ∙

research

∙ 08/27/2020

A Survey of Evaluation Metrics Used for NLG Systems

The success of Deep Learning has created a surge in interest in a wide a...

0 Ananya B. Sai, et al. ∙

research

∙ 08/13/2020

On the Importance of Local Information in Transformer Based Models

The self-attention module is a key component of Transformer-based models...

0 Madhura Pande, et al. ∙

research

∙ 07/05/2020

A Systematic Evaluation of Object Detection Networks for Scientific Plots

Are existing object detection methods adequate for detecting text and vi...

10 Pritha Ganguly, et al. ∙

research

∙ 05/28/2020

On Incorporating Structural Information to improve Dialogue Response Generation

We consider the task of generating dialogue responses from background kn...

0 Nikita Moghe, et al. ∙

research

∙ 04/30/2020

AI4Bharat-IndicNLP Corpus: Monolingual Corpora and Word Embeddings for Indic Languages

We present the IndicNLP corpus, a large-scale, general-domain corpus con...

0 Anoop Kunchukuttan, et al. ∙

research

∙ 04/29/2020

Towards Transparent and Explainable Attention Models

Recent studies on interpretability of attention distributions have led t...

0 Akash Kumar Mohankumar, et al. ∙

research

∙ 11/03/2019

Scene Graph based Image Retrieval – A case study on the CLEVR Dataset

With the prolification of multimodal interaction in various domains, rec...

0 Sahana Ramnath, et al. ∙

research

∙ 09/03/2019

Data Interpretation over Plots

Reasoning over plots by question answering (QA) is a challenging machine...

0 Nitesh Methani, et al. ∙

research

∙ 08/31/2019

Let's Ask Again: Refine Network for Automatic Question Generation

In this work, we focus on the task of Automatic Question Generation (AQG...

0 Preksha Nema, et al. ∙

research

∙ 04/04/2019

Frustratingly Poor Performance of Reading Comprehension Models on Non-adversarial Examples

When humans learn to perform a difficult task (say, reading comprehensio...

0 Soham Parikh, et al. ∙

research

∙ 04/04/2019

ElimiNet: A Model for Eliminating Options for Reading Comprehension with Multiple Choice Questions

The task of Reading Comprehension with Multiple Choice Questions, requir...

0 Soham Parikh, et al. ∙

research

∙ 02/27/2019

Efficient Video Classification Using Fewer Frames

Recently,there has been a lot of interest in building compact models for...

0 Shweta Bhardwaj, et al. ∙

research

∙ 02/23/2019

Re-evaluating ADEM: A Deeper Look at Scoring Dialogue Responses

Automatically evaluating the quality of dialogue responses for unstructu...

0 Ananya B. Sai, et al. ∙

research

∙ 12/26/2018

Studying the Plasticity in Deep Convolutional Neural Networks using Random Pruning

Recently there has been a lot of work on pruning filters from deep convo...

12 Deepak Mittal, et al. ∙

research

∙ 10/29/2018

On Controllable Sparse Alternatives to Softmax

Converting an n-dimensional vector to a probability distribution over n ...

0 Anirban Laha, et al. ∙

research

∙ 09/21/2018

Towards Exploiting Background Knowledge for Building Conversation Systems

Existing dialog datasets contain a sequence of utterances and responses ...

0 Nikita Moghe, et al. ∙

research

∙ 08/30/2018

Towards a Better Metric for Evaluating Question Generation Systems

There has always been criticism for using n-gram based similarity metric...

0 Preksha Nema, et al. ∙

research

∙ 06/15/2018

A Dataset for Building Code-Mixed Goal Oriented Conversation Systems

There is an increasing demand for goal-oriented conversation systems whi...

0 Suman Banerjee, et al. ∙

research

∙ 06/12/2018

A Question-Answering framework for plots using Deep learning

Deep Learning has managed to push boundaries in a wide variety of tasks....

0 Revanth Reddy, et al. ∙

research

∙ 05/31/2018

Fusion Graph Convolutional Networks

Semi-supervised node classification involves learning to classify unlabe...

0 Priyesh Vijayan, et al. ∙

research

∙ 05/31/2018

HOPF: Higher Order Propagation Framework for Deep Collective Classification

Given a graph wherein every node has certain attributes associated with ...

0 Priyesh Vijayan, et al. ∙

research

∙ 05/12/2018

I Have Seen Enough: A Teacher Student Network for Video Classification Using Fewer Frames

Over the past few years, various tasks involving videos such as classifi...

0 Shweta Bhardwaj, et al. ∙

research

∙ 04/21/2018

DuoRC: Towards Complex Language Understanding with Paraphrased Reading Comprehension

We propose DuoRC, a novel dataset for Reading Comprehension (RC) that mo...

0 Amrita Saha, et al. ∙

Mitesh M. Khapra

Featured Co-authors