AI-Driven Multilingual Document Analysis and Interaction System
Article Sidebar
Main Article Content
Abstract
This research paper introduces a pioneering application that integrates the capabilities of Artificial Intelligence (AI) with document-based interactions. Users can effortlessly upload their preferred documents to the system, enabling AI analysis of the document's content. Following this analysis, users can pose questions related to the document's content. The application harnesses natural language understanding and AI-driven processing to provide comprehensive and insightful answers, effectively transforming static documents into dynamic repositories of interactive knowledge. By seamlessly integrating document processing and natural language comprehension, this paper aims to redefine and elevate the user experience of interacting with information. Whether utilized for research, learning endeavors, or exploration, this application stands out to enhance user engagement and, facilitating smarter and more interactive interactions with documents.
Downloads
Article Details
Section
This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite
References
S. CS224N, D. Project, G. K. Sullan, T. E. Truong, Mentor, and Y. Zhang, “Using Character Embedding and QANet to Improve Perfomance on Question-Answering Task (SQuAD),” 2022.
K. Karpagam, K. Karpagam, A. Saradha, A. Saradha, and A. Saradha, “A framework for intelligent question answering system using semantic context-specific document clustering and Wordnet,” Sadhana-academy Proceedings in Engineering Sciences, 2019, doi: 10.1007/s12046-018-1022-8.
A. Wang et al., “GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding,” BlackboxNLP@EMNLP, 2019, doi: 10.18653/v1/w18-5446.
G N, Basavaraj et.al. (2023). Hybrid Approach for Retail Store Auditing Using CRNN. 1-7. 10.1109/NMITCON58196.2023.10276301. Date of Conference: September 01-02, 2023.
Reliability-driven time series data analysis in multiple-level deep Learning methods utilizing soft computing methods, Measurement: Sensors, Volume 24, Journal ISSN:2665-9174, https://doi.org/10.1016/j.measen.2022.100501, 29 September 2022. https://www.sciencedirect.com/science/article/pii/S2665917422001350
G. Barlacchi et al., “FocusQA: Open-Domain Question Answering with a Context in Focus,” Conference on Empirical Methods in Natural Language Processing, 2022, doi: 10.18653/v1/2022.findings-emnlp.381.
S. Yoon, S. Yoon, E. Rhim, E. Rhim, D. Kim, and D. Kim, “Domain Question Answering System,” 2015, doi: 10.5626/ktcp.2015.21.2.144.
J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,” North American Chapter of the Association for Computational Linguistics, 2019, doi: 10.18653/v1/n19-1423.
K. S. D. Ishwari et al., “Advances in Natural Language Question Answering: A Review.”
H. Naveed et al., “A Comprehensive Overview of Large Language Models,” arXiv.org, 2023, doi: 10.48550/arxiv.2307.06435.
S. Minaee, E. Cambria, and J. Gao, “Deep Learning–based Text Classification,” ACM Computing Surveys (CSUR), vol. 54, pp. 1–40, 2020, [Online]. Available: https://api.semanticscholar.org/CorpusID:235386502
M. Lewis et al., “BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension.,” arXiv: Computation and Language, 2019, doi: 10.18653/v1/2020.acl-main.703.
G. Qiang, S. Tang, J. Hao, and L. Sarno, “A BIM and AIoT Integration Framework for Improving Energy Efficiency in Green Buildings,” Construction Research Congress 2024, 2024, doi: 10.1061/9780784485262.059.
S. Manathunga and Y. A. Illangasekara, “Retrieval Augmented Generation and Representative Vector Summarization for large unstructured textual data in Medical Education,” arXiv.org, 2023, doi: 10.48550/arxiv.2308.00479.
L. Wang, Y. Liu, X. Zhao, and Y. Xu, “Particle Swarm Optimization for Fuzzy c-Means Clustering,” in 2006 6th World Congress on Intelligent Control and Automation, 2006, pp. 6055–6058. doi: 10.1109/WCICA.2006.1714243.
T. Dao, D. Y. Fu, S. Ermon, A. Rudra, and C. Ré, “FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness,” 2022. [Online]. Available: https://arxiv.org/abs/2205.14135.
S. Sarawagi and S. Sarawagi, “Models and indices for integrating unstructured data with a relational database,” InternationalWorkshop on Knowledge Discovery in Inductive Databases, 2004, doi: 10.1007/978-3-540-3184.