Ontology-based prompt tuning for news article summarization

Ontology-based prompt tuning and abstractive text summarization techniques represent an advanced approach to enhancing the quality and contextual relevance of news article summaries. Despite the progress in natural language processing (NLP) and machine learning, existing methods often rely on extractive summarization, which lacks the ability to generate coherent and contextually rich summaries. Moreover, these approaches rarely integrate domain-specific knowledge, resulting in generic and sometimes inaccurate summaries. In this study, we propose a novel framework, which combines ontology-based prompt tuning with abstractive text summarization to address these limitations. By leveraging ontological knowledge, our model fine-tunes the summarization process, ensuring that the generated summaries are not only accurate but also contextually relevant to the domain. This integration allows for a more nuanced understanding of the text, enabling the generation of summaries that better capture the essence of the news articles. Our evaluation results demonstrate significant improvements over state-of-the-art methods such as BART, BERT, and GPT-3.5. The results show that the proposed architecture achieved a 5.1% higher ROUGE-1 score and a 9.8% improvement in ROUGE-L compared to baseline models. Additionally, our model showed significance in F1, precision, and recall metrics, with major improvements of 6.7, 3.9, and 4.8%, respectively. These results underscore the effectiveness of integrating ontological insights into the prompt tuning process, offering a robust solution for generating high-quality, domain-specific news summaries.