Cross-Lingual Transfer vs. Minimal Fine-Tuning for Indic Question Answering: An Empirical Study on the Indic-QA Benchmark Manash Pratim Lahkar, Utpal Sharma, Tribikram Pradhan Fire 2025 Proceedings of the 17th Annual Meeting of the Forum for Information Retrieval Evaluation, 2026 The development of robust Question Answering (QA) systems for the linguistically diverse and resource-constrained Indian subcontinent presents a significant challenge in Natural Language Processing. This paper investigates two primary paradigms for leveraging large pre-trained models in this context: zero-shot cross-lingual transfer and minimal, data-efficient fine-tuning. We conduct a rigorous empirical study on the Indic-QA dataset, a comprehensive dataset for extractive QA covering 11 major Indian languages. Our analysis begins with a comparative evaluation of four prominent transformer-based models, revealing the superior zero-shot transfer capabilities of the XLM-RoBERTa architecture, with the deepset/xlm-roberta-large-squad2 model establishing the state-of-the-art in this setting. Subsequently, we demonstrate the impact of minimal adaptation; fine-tuning this top-performing model on just a single epoch of a 50% subset of the training data yields clear and consistent performance gains, increasing the average F1 score across all 11 languages and demonstrating that even a modest adaptation effort can significantly enhance the model’s baseline cross-lingual capabilities. These findings provide a practical guide for practitioners, highlighting that while larger models provide a strong zero-shot baseline, targeted, albeit minimal, adaptation is a valuable strategy for building higher-performance QA systems in low-resource Indic settings.
SEHRS: Sentiment-Enhanced Hybrid Recommender System for Personalized News Recommendation Dhanjit Kalita, Tribikram Pradhan 2025 5th Asian Conference on Innovation in Technology Asiancon 2025, 2025 Personalized news recommendation faces unique challenges including dynamic user preferences, content diversity requirements and the cold start problem. This paper presents SEHRS (Sentiment-Enhanced Hybrid Recommender System) a novel approach that integrates knowledge-aware features (KRED), Deep-Attention Neural Network (DAN) and sentiment analysis for enhanced news recommendation. We evaluate SEHRS against content-based filtering, collaborative filtering, KRED and DAN baselines on a custom MIND-like dataset using 12 comprehensive evaluation metrics. Our experimental results demonstrate that SEHRS achieves superior performance across 8 out of 12 metrics, particularly excelling in Average Precision (0.5155), Mean Reciprocal Rank (0.6014), NDCG@5 (0.4334), and Diversity (0.8000). The hybrid approach effectively combines the strengths of knowledge-aware recommendations, attention-based feature weighting, and sentiment analysis to provide balanced performance across ranking quality, diversity and coverage metrics.
When Graphs Meet Fine-Tuning: A Dual Approach to Low-Resource Assamese QA Manash Pratim Lahkar, Utpal Sharma, Tribikram Pradhan 6th IEEE International Conference on Recent Advances in Information Technology Rait 2025, 2025 This paper introduces a novel framework designed to tackle question-answering tasks, with a focus on low-resource languages: Assamese. The framework employs two distinct methodologies: an unsupervised graph-based approach that leverages Named Entity Recognition, graph embeddings, and similarity techniques, alongside a supervised approach that finetunes pretrained models to enhance performance. We created a dataset which consists of $\mathbf{1 0 0}$ distinct contexts, each containing $\mathbf{1 0}$ extractive questions and their corresponding answers, all placed sequentially within the context. Through rigorous experimentation, we demonstrate the effectiveness of these methodologies. The Muril model, a leading pretrained model for Indic languages, achieved an exact match score of 62 and an F1 score of 75.44, making it the top performer. On the other hand, the unsupervised graph-based approach yielded a promising F1 score of 45.92, showcasing its potential for domain-specific tasks in low-resource settings. These findings contribute to the field of Natural Language Processing by offering scalable solutions for developing question-answering systems, particularly for underresourced languages.
Brain-Inspired Software Architecture: An Adaptive Neural Network Systems Ashish Ranjan, Sushant Kumar Pandey, Ashwini Kumar Singh, Tribikram Pradhan Proceedings IEEE 21st International Conference on Software Architecture Companion Icsa C 2024, 2024 The paper presents a new idea of software architecture inspired by the processing mechanism of the human brain. Stimulated by the working of the human brain, we propose an adaptive neural network software architecture that integrates the principles of neuroevolution for adjusting activation functions and an adaptive mechanism for selecting varying numbers of hidden layers to dynamically adjust the structure, functions, and parameters of the neural network. Utilizing genetic algorithms like crossover and mutation strengthens the architecture to optimize its components to adapt in situations like varying data distribution and learning objectives. We conducted an initial experiment on two benchmark image datasets (MNIST and CIFAR-10) and compared the performance for classification, clustering, and reinforcement learning tasks. We found that applying the proposed architecture with a neural network produces 51% better results. We also found that the results are comparable and better for clustering and reinforcement tasks on both datasets. The article concludes that the proposed architecture improves the performance of these machine-learning tasks over classical techniques and can offer a framework for developing robust and adaptable neural network systems.
An Efficient Solution to User Authorization Query Problem in RBAC Systems Using Hierarchical Clustering K. Rajesh Rao, Aditya Kolpe, Tribikram Pradhan, Bruno Bogaz Zarpelão Journal of Cyber Security and Mobility, 2022 Role Based Access Control (RBAC) systems face an essential issue related to systematic handling of users’ access requests known as the User Authentication Query (UAQ) Problem. In this paper, we show that the UAQ problem can be resolved using Unsupervised machine learning following the guaranteed access request and Dynamic Separation of Duty relations. The use of Agglomerative Hierarchical Clustering not only improves efficiency but also avoids disordered merging of existing roles to create new ones and steers clear of duplication. With a time complexity of O(n^3), the algorithm proves to be one of the fastest and promising models in state-of-the-art. The proposed model has been compared with the existing models and experimentally evaluated.
CLAVER: An integrated framework of convolutional layer, bidirectional LSTM with attention mechanism based scholarly venue recommendation Tribikram Pradhan, Prashant Kumar, Sukomal Pal Information Sciences, 2021 Scholarly venue recommendation is an emerging field due to a rapid surge in the number of scholarly venues concomitant with exponential growth in interdisciplinary research and cross collaboration among researchers. Finding appropriate publication venues is confronted as one of the most challenging aspects in paper publication as a larger proportion of manuscripts face rejection due to a disjunction between the scope of the venue and the field of research pursued by the research article. We present CLAVERG??an integrated framework of Convolutional Layer, bi-directional LSTM with an Attention mechanism-based scholarly VEnue Recommender system. The system is the first of its kind to integrate multiple deep learning-based concepts, that only requiring only the abstract and title of a manuscript to identify academic venues. An extensive and exhaustive set of experiments conducted on the DBLP dataset certify that the postulated model CLAVER performs better than most of the modern techniques as entrenched by standard metrics such as stability, accuracy, MRR, average venue quality, precision@k, nDCG@k and diversity.
A proactive decision support system for reviewer recommendation in academia Tribikram Pradhan, Suchit Sahoo, Utkarsh Singh, Sukomal Pal Expert Systems with Applications, 2021 Peer review is an essential part of scientific communications to ensure the quality of publications and a healthy scientific evaluation process. Assigning appropriate reviewers poses a great challenge for program chairs and journal editors for many reasons, including relevance, fair judgment, no conflict of interest, and qualified reviewers in terms of scientific impact. With a steady increase in the number of research domains, scholarly venues, researchers, and papers in academia, manually selecting and accessing adequate reviewers is becoming a tedious and time-consuming task. Traditional approaches for reviewer selection mainly focus on the matching of research relevance by keywords or disciplines. However, in real-world systems, various factors are often needed to be considered. Therefore, we propose a multilayered approach integrating Topic Network, Citation Network, and Reviewer Network into a reviewer Recommender System (TCRRec). We explore various aspects, including relevance between reviewer candidates and submission, authority, expertise, di- versity, and conflict of interest and integrate them into the proposed framework TCRRec. The proposed system also considers the temporal changes of reviewers’ interest and the stability of reviewers’ interests trends to enhance their performance. The paper also addresses cold start issues for researchers having unique areas of interest or for isolated researchers. Experiments based on the NIPS and AMiner dataset demonstrate that the proposed TCRRec outperforms state-of-the-art recommendation techniques in terms of standard metrics of precision@k, MRR, nDCG@k, authority, expertise, diversity, and coverage.
A deep neural architecture based meta-review generation and final decision prediction of a scholarly article Tribikram Pradhan, Chaitanya Bhatia, Prashant Kumar, Sukomal Pal Neurocomputing, 2021 Peer reviews form an essential part of scientific communications. Research papers and proposals are reviewed by several peers before they are finally accepted or rejected for publication and funding, respectively. With the steady increase in the number of research domains, scholarly venues (journal and/or conference), researchers, and papers, managing the peer review process is becoming a daunting task. Application of recommender systems to assist peer reviewing is, therefore, being explored and becoming an emerging research area. In this paper, we present a deep learning network based Meta-Review Generation considering peer review prediction of the scholarly article (MRGen). MRGen is able to provide solutions for: (i) Peer review prediction (Task 1) and (ii) Meta-review generation (Task 2). First, the system takes the peer reviews as input and produces a draft meta-review. Then it employs an integrated framework of convolution layer, long short-term memory (LSTM) model, Bi-LSTM model, and attention mechanism to predict the final decision (accept/reject) of the scholarly article. Based on the final decision, the proposed model MRGen incorporates Pointer Generator Network-based abstractive summarization to generate the final meta-review. The focus of our approach is to give a concise meta-review that maximizes information coverage, coherence, readability and also reduces redundancy. Extensive experiments conducted on the PeerRead dataset demonstrate good consistency between the recommended decisions and original decisions. We also compare the performance of MRGen with some of the existing state-of-the-art multi-document summarization methods. The system also outperforms a few existing models based on accuracy, Rouge scores, readability, non-redundancy, and cohesion.
Context-Aware Influential Nodes Tracking in Online Social Networks Pacific Asia Conference on Information Systems, 2021
MetaGen: An academic Meta-review Generation system Chaitanya Bhatia, Tribikram Pradhan, Sukomal Pal SIGIR 2020 Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, 2020
Merge sort enhanced in place sorting algorithm R Vignesh, Tribikram Pradhan Proceedings of 2016 International Conference on Advanced Communication Control and Computing Technologies Icaccct 2016, 2017
ASIC implementation of DDR SDRAM memory controller A. Bakshi, S. S. Pandey, T. Pradhan, R. Dey 2013 IEEE International Conference on Emerging Trends in Computing Communication and Nanotechnology ICE Ccn 2013, 2013
Design of framework for logic synthesis engine International Journal of Engineering and Technology, 2013
A solution for network life time problem using content based energy efficient routing algorithm International Journal of Engineering and Technology, 2013
