134 citations · 546 across the 43 of their papers we have counts for
45 papers
Robust Marathi Sentiment Analysis using Domain-Adaptive Pre-training and Data Augmentation Approaches
Tanvi Somani, Aryan Babare, Samyak Bora +2
For languages with limited resources, Sentiment Analysis remains a challenging problem due to limited annotated data and strong domain variability across textual sources. Marathi,…
Enhancing Zero-Shot Domain Transfer in Low-Resource Sentiment Analysis: A Case Study in Marathi
Tanvi Somani, Aryan Babare, Samyak Bora +1
Sentiment analysis is a key task in Natural Language Processing that determines the polarity of opinions in text. For low-resource languages like Marathi--where limited data preven…
Minitron-SSM: Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning
Ali Taghibakhshi, Sharath Turuvekere Sreenivas, Saurav Muralidharan +15
Hybrid LLM architectures that combine Attention and State Space Models (SSMs) achieve state-of-the-art accuracy and runtime performance. Recent work has demonstrated that applying…
Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models
NVIDIA, :, Aaron Blakeman +198
As inference-time scaling becomes critical for enhanced reasoning capabilities, it is increasingly becoming important to build models that are efficient to infer. We introduce Nemo…
LLM Pruning and Distillation in Practice: The Minitron Approach
Sharath Turuvekere Sreenivas, Saurav Muralidharan, Raviraj Joshi +19
We present a comprehensive report on compressing the Llama 3.1 8B and Mistral NeMo 12B models to 4B and 8B parameters, respectively, using pruning and distillation. We explore two…
Compact Language Models via Pruning and Knowledge Distillation
Saurav Muralidharan, Sharath Turuvekere Sreenivas, Raviraj Joshi +6
Large language models (LLMs) targeting different deployment scales and sizes are currently produced by training each variant from scratch; this is extremely compute-intensive. In t…
L3Cube-MahaNews: News-based Short Text and Long Document Classification Datasets in Marathi
Saloni Mittal, Vidula Magdum, Omkar Dhekane +2
The availability of text or topic classification datasets in the low-resource Marathi language is limited, typically consisting of fewer than 4 target labels, with some achieving n…
My Boli: Code-mixed Marathi-English Corpora, Pretrained Language Models and Evaluation Benchmarks
Tanmay Chavan, Omkar Gokhale, Aditya Kane +2
The research on code-mixed data is limited due to the unavailability of dedicated code-mixed datasets and pre-trained language models. In this work, we focus on the low-resource In…
L3Cube-MahaSent-MD: A Multi-domain Marathi Sentiment Analysis Dataset and Transformer Models
Aabha Pingle, Aditya Vyawahare, Isha Joshi +2
The exploration of sentiment analysis in low-resource languages, such as Marathi, has been limited due to the availability of suitable datasets. In this work, we present L3Cube-Mah…
Enhancing Low Resource NER Using Assisting Language And Transfer Learning
Maithili Sabane, Aparna Ranade, Onkar Litake +3
Named Entity Recognition (NER) is a fundamental task in NLP that is used to locate the key information in text and is primarily applied in conversational and search systems. In com…
Leveraging Language Identification to Enhance Code-Mixed Text Classification
Gauri Takawane, Abhishek Phaltankar, Varad Patwardhan +3
The usage of more than one language in the same text is referred to as Code Mixed. It is evident that there is a growing degree of adaption of the use of code-mixed data, especiall…
Comparative Study of Pre-Trained BERT Models for Code-Mixed Hindi-English Data
Aryan Patil, Varad Patwardhan, Abhishek Phaltankar +2
The term "Code Mixed" refers to the use of more than one language in the same text. This phenomenon is predominantly observed on social media platforms, with an increasing amount o…
L3Cube-IndicSBERT: A simple approach for learning cross-lingual sentence representations using multilingual BERT
Samruddhi Deode, Janhavi Gadre, Aditi Kajale +2
The multilingual Sentence-BERT (SBERT) models map different languages to common representation space and are useful for cross-language similarity and mining tasks. We propose a sim…
A Twitter BERT Approach for Offensive Language Detection in Marathi
Tanmay Chavan, Shantanu Patankar, Aditya Kane +2
Automated offensive language detection is essential in combating the spread of hate speech, particularly in social media. This paper describes our work on Offensive Language Identi…
Implementing Deep Learning-Based Approaches for Article Summarization in Indian Languages
Rahul Tangsali, Aabha Pingle, Aditya Vyawahare +2
The research on text summarization for low-resource Indian languages has been limited due to the availability of relevant datasets. This paper presents a summary of various deep-le…
L3Cube-MahaSBERT and HindSBERT: Sentence BERT Models and Benchmarking BERT Sentence Representations for Hindi and Marathi
Ananya Joshi, Aditi Kajale, Janhavi Gadre +2
Sentence representation from vanilla BERT models does not work well on sentence similarity tasks. Sentence-BERT models specifically trained on STS or NLI datasets are shown to prov…
L3Cube-HindBERT and DevBERT: Pre-Trained BERT Transformer models for Devanagari based Hindi and Marathi Languages
Raviraj Joshi
The monolingual Hindi BERT models currently available on the model hub do not perform better than the multi-lingual models on downstream tasks. We present L3Cube-HindBERT, a Hindi…
Spread Love Not Hate: Undermining the Importance of Hateful Pre-training for Hate Speech Detection
Omkar Gokhale, Aditya Kane, Shantanu Patankar +2
Pre-training large neural language models, such as BERT, has led to impressive gains on many natural language processing (NLP) tasks. Although this method has proven to be effectiv…
Towards Simple and Efficient Task-Adaptive Pre-training for Text Classification
Arnav Ladkat, Aamir Miyajiwala, Samiksha Jagadale +2
Language models are pre-trained using large corpora of generic data like book corpus, common crawl and Wikipedia, which is essential for the model to understand the linguistic char…
A Review of Challenges in Machine Learning based Automated Hate Speech Detection
Abhishek Velankar, Hrushikesh Patil, Raviraj Joshi
The spread of hate speech on social media space is currently a serious issue. The undemanding access to the enormous amount of information being generated on these platforms has le…
On Comparison of Encoders for Attention based End to End Speech Recognition in Standalone and Rescoring Mode
Raviraj Joshi, Subodh Kumar
The streaming automatic speech recognition (ASR) models are more popular and suitable for voice-based applications. However, non-streaming models provide better performance as they…
A Simple Baseline for Domain Adaptation in End to End ASR Systems Using Synthetic Data
Raviraj Joshi, Anupam Singh
Automatic Speech Recognition(ASR) has been dominated by deep learning-based end-to-end speech recognition models. These approaches require large amounts of labeled data in the form…
L3Cube-MahaNLP: Marathi Natural Language Processing Datasets, Models, and Library
Raviraj Joshi
Despite being the third most popular language in India, the Marathi language lacks useful NLP resources. Moreover, popular NLP libraries do not have support for the Marathi languag…
Mono vs Multilingual BERT for Hate Speech Detection and Text Classification: A Case Study in Marathi
Abhishek Velankar, Hrushikesh Patil, Raviraj Joshi
Transformers are the most eminent architectures used for a vast range of Natural Language Processing tasks. These models are pre-trained over a large text corpus and are meant to s…