Browsing by Author "Sahil, M."

Now showing 1 - 3 of 3

A review on NLP zero-shot and few-shot learning: methods and applications
(Springer Nature, 2025) Ramesh, G.; Sahil, M.; Palan, S.A.; Bhandary, D.; Ashok, T.A.; J, J.; Sowjanya, N.
Zero-shot and few-shot learning techniques in natural language processing (NLP), this comprehensive review traces their evolution from traditional methods to cutting-edge approaches like transfer learning and pre-trained language models, semantic embedding, attribute-based approaches, generative models for data augmentation in zero-shot learning, and meta-learning, model-agnostic meta-learning, relationship networks, model-agnostic meta-learning (MAML), prototypical networks in few-shot learning. Real-world applications underscore the adaptability and efficacy of these techniques across various NLP tasks in both industry and academia. Acknowledging challenges inherent in zero-shot and few-shot learning, this review identifies limitations and suggests avenues for improvement. It emphasizes theoretical foundations alongside practical considerations such as accuracy and generalization across diverse NLP tasks. By consolidating key insights, this review provides researchers and practitioners with valuable guidance on the current state and future potential of zero-shot and few-shot learning techniques in addressing real-world NLP challenges. Looking ahead, this review aims to stimulate further research, fostering a deeper understanding of the complexities and applicability of zero-shot and few-shot learning techniques in NLP. By offering a roadmap for future exploration, it seeks to contribute to the ongoing advancement and practical implementation of NLP technologies across various domains. Â© The Author(s) 2025.
A review on NLP zero-shot and few-shot learning: methods and applications
(Springer Nature, 2025) Ramesh, G.; Sahil, M.; Palan, S.A.; Bhandary, D.; Ashok, T.A.; J, J.; Sowjanya, N.
Zero-shot and few-shot learning techniques in natural language processing (NLP), this comprehensive review traces their evolution from traditional methods to cutting-edge approaches like transfer learning and pre-trained language models, semantic embedding, attribute-based approaches, generative models for data augmentation in zero-shot learning, and meta-learning, model-agnostic meta-learning, relationship networks, model-agnostic meta-learning (MAML), prototypical networks in few-shot learning. Real-world applications underscore the adaptability and efficacy of these techniques across various NLP tasks in both industry and academia. Acknowledging challenges inherent in zero-shot and few-shot learning, this review identifies limitations and suggests avenues for improvement. It emphasizes theoretical foundations alongside practical considerations such as accuracy and generalization across diverse NLP tasks. By consolidating key insights, this review provides researchers and practitioners with valuable guidance on the current state and future potential of zero-shot and few-shot learning techniques in addressing real-world NLP challenges. Looking ahead, this review aims to stimulate further research, fostering a deeper understanding of the complexities and applicability of zero-shot and few-shot learning techniques in NLP. By offering a roadmap for future exploration, it seeks to contribute to the ongoing advancement and practical implementation of NLP technologies across various domains. © The Author(s) 2025.
Inorganic Chemical Reaction Predictor Using Random Forest and Support Vector Machine
(Institute of Electrical and Electronics Engineers Inc., 2025) Ramesh, G.; Sahil, M.; Palan, S.A.; Bhandary, D.; Shetty, S.S.; Poojary, K.K.; Sowjanya, N.
The Chemical Reaction Predictor project shall use machine learning approaches to make predictions on chemical reaction effects. When a large enough group of known reactions is available, each identified set of reactants and products can be used to construct a model into which can be fed any set of reactants. It includes data acquisition and data pre-processing, feature selection of reactant properties and reaction conditions, and construction of several predictive models. The first and main goal is to dogmatically apply machine learning models such as Random Forests and Support Vector Machines to attain an accuracy of 60% or higher. Furthermore, we measure the accuracy, and other measures such as precision, recall, and F1 score to determine the efficiency of these models. Finally, while the optimal model is found and implemented, it is brought within a simple graphical user interface that enables the users to input reactants and obtain predicted products. Â© 2025 IEEE.