Machine Learning-Based System for Automated Presentation Generation from CSV Data

Balusamy Nachiappan Balusamy Nachiappan, N Rajkumar, C Kalpana, A Mohanraj, B Prabhu Shankar and C Viji

Data and Metadata, 2024, vol. 3, 359

Abstract: Effective presentation slides are crucial for conveying information efficiently, yet existing tools lack content analysis capabilities. This paper introduces a content-based PowerPoint presentation generator, aiming to address this gap. By leveraging automated techniques, slides are generated from text documents, ensuring original concepts are effectively communicated. Unstructured data poses challenges for organizations, impacting productivity and profitability. While traditional methods fall short, AI-based approaches offer promise. This systematic literature review (SLR) explores AI methods for extracting data from unstructured details. Findings reveal limitations in existing methods, particularly in handling complex document layouts. Moreover, publicly available datasets are task-specific and of low quality, highlighting the need for comprehensive datasets reflecting real-world scenarios. The SLR underscores the potential of Artificial-based approaches for information extraction but emphasizes the challenges in processing diverse document layouts. The proposed is a framework for constructing high-quality datasets and advocating for closer collaboration between businesses and researchers to address unstructured data challenges effectively

Date: 2024
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:dbk:datame:v:3:y:2024:i::p:359:id:1056294dm2024359

DOI: 10.56294/dm2024359

Access Statistics for this article

More articles in Data and Metadata from AG Editor
Bibliographic data for series maintained by Javier Gonzalez-Argote ().