Search Results for author:
Found 42 papers, 18 papers with code
On the weak link between importance and prunability of attention heads
Given the success of Transformer-based models, two directions of study have emerged: interpreting role of individual attention heads and down-sizing the models for efficiency.
Empowering Low-Resource Language ASR via Large-Scale Pseudo Labeling
In this study, we tackle the challenge of limited labeled data for low-resource languages in ASR, focusing on Hindi.
RoundTable: Leveraging Dynamic Schema and Contextual Autocomplete for Enhanced Query Precision in Tabular Question Answering
With advancements in Large Language Models (LLMs), a major use case that has emerged is querying databases in plain English, translating user questions into executable database queries, which has improved significantly.
IndicLLMSuite: A Blueprint for Creating Pre-training and Fine-Tuning Datasets for Indian Languages
We hope that the datasets, tools, and resources released as a part of this work will not only propel the research and development of Indic LLMs but also establish an open-source blueprint for extending such efforts to other languages.
IndicVoices: Towards building an Inclusive Multilingual Speech Dataset for Indian Languages
We present INDICVOICES, a dataset of natural and spontaneous speech containing a total of 7348 hours of read (9%), extempore (74%) and conversational (17%) audio from 16237 speakers covering 145 Indian districts and 22 languages.
DSFormer: Effective Compression of Text-Transformers by Dense-Sparse Weight Factorization
Extensive experiments on multiple natural language understanding benchmarks demonstrate that DSFormer obtains up to 40% better compression than the state-of-the-art low-rank factorizers, leading semi-structured sparsity baselines and popular knowledge distillation approaches.
Svarah: Evaluating English ASR Systems on Indian Accents
India is the second largest English-speaking country in the world with a speaker base of roughly 130 million.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
IndicTrans2: Towards High-Quality and Accessible Machine Translation Models for all 22 Scheduled Indian Languages
Prior to this work, there was (i) no parallel training data spanning all 22 languages, (ii) no robust benchmarks covering all these languages and containing content relevant to India, and (iii) no existing translation models which support all the 22 scheduled languages of India.
Vistaar: Diverse Benchmarks and Training Sets for Indian Language ASR
In this paper, we focus on Indian languages, and make the case that diverse benchmarks are required to evaluate and improve ASR systems for Indian languages.
Large Language Models Humanize Technology
Given this opportunity to humanize technology widely, we advocate for more widespread understanding of LLMs, tools and methods to simplify use of LLMs, and cross-cutting institutional capacity.
An Empirical Study of Leveraging Knowledge Distillation for Compressing Multilingual Neural Machine Translation Models
Knowledge distillation (KD) is a well-known method for compressing neural models.
Naamapadam: A Large-Scale Named Entity Annotated Data for Indic Languages
The dataset contains more than 400k sentences annotated with a total of at least 100k entities from three standard entity categories (Person, Location, and, Organization) for 9 out of the 11 languages.
IndicMT Eval: A Dataset to Meta-Evaluate Machine Translation metrics for Indian Languages
In this paper, we fill this gap by creating an MQM dataset consisting of 7000 fine-grained annotations, spanning 5 Indian languages and 7 MT systems, and use it to establish correlations between annotator scores and scores obtained using existing automatic metrics.
Towards Leaving No Indic Language Behind: Building Monolingual Corpora, Benchmark and Models for Indic Languages
Across languages and tasks, IndicXTREME contains a total of 105 evaluation sets, of which 52 are new contributions to the literature.
Towards Building Text-To-Speech Systems for the Next Billion Users
We open-source all models on the Bhashini platform.
Ranked #1 on
Speech Synthesis - Hindi
on IndicTTS
Efficient ML Models for Practical Secure Inference
For instance, the model provider could be a diagnostics company that has trained a state-of-the-art DenseNet-121 model for interpreting a chest X-ray and the user could be a patient at a hospital.
Effectiveness of Mining Audio and Text Pairs from Public Data for Improving ASR Systems for Low-Resource Languages
Significantly, we show that adding Shrutilipi to the training set of Wav2Vec models leads to an average decrease in WER of 5. 8\% for 7 languages on the IndicSUPERB benchmark.
IndicSUPERB: A Speech Processing Universal Performance Benchmark for Indian languages
We hope IndicSUPERB contributes to the progress of developing speech language understanding models for Indian languages.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+6
Aksharantar: Open Indic-language Transliteration datasets and models for the Next Billion Users
Transliteration is very important in the Indian language context due to the usage of multiple scripts and the widespread use of romanized inputs.
Joint Transformer/RNN Architecture for Gesture Typing in Indic Languages
Gesture typing is a method of typing words on a touch-based keyboard by creating a continuous trace passing through the relevant keys.
Input-specific Attention Subnetworks for Adversarial Detection
We also demonstrate that our method (a) is more accurate for larger models which are likely to have more spurious correlations and thus vulnerable to adversarial attack, and (b) performs well even with modest training sets of adversarial examples.
IndicNLG Benchmark: Multilingual Datasets for Diverse NLG Tasks in Indic Languages
Natural Language Generation (NLG) for non-English languages is hampered by the scarcity of datasets in these languages.
Towards Building ASR Systems for the Next Billion Users
Second, using this raw speech data we pretrain several variants of wav2vec style models for 40 Indian languages.
OpenHands: Making Sign Language Recognition Accessible with Pose-based Pretrained Models across Languages
Third, to address the lack of labelled data, we propose self-supervised pretraining on unlabelled data.
SuperShaper: Task-Agnostic Super Pre-training of BERT Models with Variable Hidden Dimensions
Such models need to be deployed on devices across the cloud and the edge with varying resource and accuracy constraints.
Machine Learning approaches to do size based reasoning on Retail Shelf objects to classify product variants
There has been a surge in the number of Machine Learning methods to analyze products kept on retail shelves images.
On the Prunability of Attention Heads in Multilingual BERT
Large multilingual models, such as mBERT, have shown promise in crosslingual transfer.
IndicBART: A Pre-trained Model for Indic Natural Language Generation
We present IndicBART, a multilingual, sequence-to-sequence pre-trained model focusing on 11 Indic languages and English.
Design and Scaffolded Training of an Efficient DNN Operator for Computer Vision on the Edge
The parameter efficiency of FuSeConv and its significant out-performance over depthwise separable convolutions on systolic arrays illustrates their promise as a strong solution on the edge.
VeRLPy: Python Library for Verification of Digital Designs with Reinforcement Learning
Digital hardware is verified by comparing its behavior against a reference model on a range of randomly generated input signals.
A Primer on Pretrained Multilingual Language Models
Multilingual Language Models (\MLLMs) such as mBERT, XLM, XLM-R, \textit{etc.}
Joint Multilingual Sentence Representations
Multilingual text classification
+5
FuSeConv: Fully Separable Convolutions for Fast Inference on Systolic Arrays
The resultant computation is systolic and efficiently utilizes the systolic array with a slightly modified dataflow.
Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languages
We mine the parallel sentences from the web by combining many corpora, tools, and methods: (a) web-crawled monolingual corpora, (b) document OCR for extracting sentences from scanned documents, (c) multilingual representation models for aligning sentences, and (d) approximate nearest neighbor search for searching in a large collection of sentences.
The heads hypothesis: A unifying statistical approach towards understanding multi-headed attention in BERT
There are two main challenges with existing methods for classification: (a) there are no standard scores across studies or across functional roles, and (b) these scores are often average quantities measured across sentences without capturing statistical significance.
Differential Euler: Designing a Neural Network approximator to solve the Chaotic Three Body Problem
In this paper, we propose a detailed experimental setup to determine the feasibility of using neural networks to solve the three body problem up to a certain number of time steps.
A Systematic Evaluation of Object Detection Networks for Scientific Plots
However, the performance drops drastically when evaluated at a stricter IOU of 0. 9 with the best model giving a mAP of 35. 70%.
AI4Bharat-IndicNLP Corpus: Monolingual Corpora and Word Embeddings for Indic Languages
We present the IndicNLP corpus, a large-scale, general-domain corpus containing 2. 7 billion words for 10 Indian languages from two language families.
Compact retail shelf segmentation for mobile deployment
In this paper, we work on one such common problem in the retail industries - Shelf segmentation.
PlotQA: Reasoning over Scientific Plots
However, in practice, this is an unrealistic assumption because many questions require reasoning and thus have real-valued answers which appear neither in a small fixed size vocabulary nor in the image.
Ranked #2 on
Chart Question Answering
on RealCQA
Example Mining for Incremental Learning in Medical Imaging
Incremental learning proves to be time as well as resource-efficient solution for deployment of deep learning algorithms in real world as the model can automatically and dynamically adapt to new data as and when annotated data becomes available.
Detection of Tooth caries in Bitewing Radiographs using Deep Learning
We develop a Computer Aided Diagnosis (CAD) system, which enhances the performance of dentists in detecting wide range of dental caries.
