@article{10.11648/j.ijsts.20251306.15,
  author = {Fransina Ahalwa and Sam Lubbe and Henry Mynhardt},
  title = {Cloud-Enabled on-Premises Business Intelligence Systems},
  journal = {International Journal of Science, Technology and Society},
  volume = {13},
  number = {6},
  pages = {287-297},
  doi = {10.11648/j.ijsts.20251306.15},
  url = {https://doi.org/10.11648/j.ijsts.20251306.15},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ijsts.20251306.15},
  abstract = {The Research Focus was on Enhancing Precision and Novelty in Language Model Abstractive Summation. The primary focus was on refining the abstractive summation capabilities of the Cloud-Enabled On-Premises Business Intelligence Systems. In the body of text, the authors specifically explored techniques to enhance both the precision and novelty of Cloud-Enabled On-Premises Business Intelligence Systems. The authors conducted a thorough analysis of the Cloud-Enabled On-Premises Business Intelligence Systems to generate factually incorrect or irrelevant statements in summaries. Based on this analysis, the authors implemented several strategies to improve precision: Fact-checking mechanisms: The authors integrated external knowledge bases and fact-checking APIs to verify the accuracy of the generated content. Contextual awareness: The authors enhanced the model's ability to consider the broader context of the input text, leading to more accurate and relevant summaries. Evaluation metrics: The authors refined their evaluation metrics to include measures that specifically assess the factual accuracy and relevance of the generated summaries. They recognized the importance of generating summaries that are not merely paraphrases of the input text but offer new insights or perspectives. To address this, they explored techniques to promote novelty: Diverse sentence generation: They also encouraged a wider variety of sentence structures and vocabulary, reducing the likelihood of repetitive or redundant summaries. Semantic exploration: The therefore implemented methods to explore different semantic interpretations of the input text, leading to more creative and informative summaries. Evaluation metrics: They incorporated metrics that measure the degree of novelty and originality in the generated summaries. Building upon yesterday's achievements, they will continue their efforts to improve the precision and novelty of the abstractive summation model. Their future work will include incorporating user feedback. They will actively seek feedback from users to identify areas for further improvement and tailor the model's output to specific preferences. Exploring additional techniques: They will investigate other promising techniques, such as reinforcement learning and generative adversarial networks, to further enhance the model's capabilities. Expanding evaluation metrics: They will continue to refine our evaluation metrics to ensure a comprehensive assessment of the model's performance. By consistently focusing on precision and novelty, they aim to develop an abstractive summation model that generates high-quality, informative, and Cloud-Enabled On-Premises Business Intelligence Systems.},
 year = {2025}
}

Copy | Download

TY  - JOUR
T1  - Cloud-Enabled on-Premises Business Intelligence Systems
AU  - Fransina Ahalwa
AU  - Sam Lubbe
AU  - Henry Mynhardt
Y1  - 2025/12/09
PY  - 2025
N1  - https://doi.org/10.11648/j.ijsts.20251306.15
DO  - 10.11648/j.ijsts.20251306.15
T2  - International Journal of Science, Technology and Society
JF  - International Journal of Science, Technology and Society
JO  - International Journal of Science, Technology and Society
SP  - 287
EP  - 297
PB  - Science Publishing Group
SN  - 2330-7420
UR  - https://doi.org/10.11648/j.ijsts.20251306.15
AB  - The Research Focus was on Enhancing Precision and Novelty in Language Model Abstractive Summation. The primary focus was on refining the abstractive summation capabilities of the Cloud-Enabled On-Premises Business Intelligence Systems. In the body of text, the authors specifically explored techniques to enhance both the precision and novelty of Cloud-Enabled On-Premises Business Intelligence Systems. The authors conducted a thorough analysis of the Cloud-Enabled On-Premises Business Intelligence Systems to generate factually incorrect or irrelevant statements in summaries. Based on this analysis, the authors implemented several strategies to improve precision: Fact-checking mechanisms: The authors integrated external knowledge bases and fact-checking APIs to verify the accuracy of the generated content. Contextual awareness: The authors enhanced the model's ability to consider the broader context of the input text, leading to more accurate and relevant summaries. Evaluation metrics: The authors refined their evaluation metrics to include measures that specifically assess the factual accuracy and relevance of the generated summaries. They recognized the importance of generating summaries that are not merely paraphrases of the input text but offer new insights or perspectives. To address this, they explored techniques to promote novelty: Diverse sentence generation: They also encouraged a wider variety of sentence structures and vocabulary, reducing the likelihood of repetitive or redundant summaries. Semantic exploration: The therefore implemented methods to explore different semantic interpretations of the input text, leading to more creative and informative summaries. Evaluation metrics: They incorporated metrics that measure the degree of novelty and originality in the generated summaries. Building upon yesterday's achievements, they will continue their efforts to improve the precision and novelty of the abstractive summation model. Their future work will include incorporating user feedback. They will actively seek feedback from users to identify areas for further improvement and tailor the model's output to specific preferences. Exploring additional techniques: They will investigate other promising techniques, such as reinforcement learning and generative adversarial networks, to further enhance the model's capabilities. Expanding evaluation metrics: They will continue to refine our evaluation metrics to ensure a comprehensive assessment of the model's performance. By consistently focusing on precision and novelty, they aim to develop an abstractive summation model that generates high-quality, informative, and Cloud-Enabled On-Premises Business Intelligence Systems.
VL  - 13
IS  - 6
ER  - 

Copy | Download