Original scientific paper

https://doi.org/10.17559/TV-20231213001202

Enhancing Text Summarization with Linguistic Prompting and Reinforcement Learning: A Human-Centered Approach

Selvi S. ; Department of Computer Science and Engineering, Government College of Engineering, Bargur, Tamil Nadu, 635104, India *
Alya Alshammari ; Department of Applied Linguistics, College of Languages, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh 11671, Saudi Arabia
Muhammad Swaileh A. Alzaidi ; Department of English Language, College of Language Sciences, King Saud University, P. O. Box 145111, Riyadh, Saudi Arabia
Karthika S. K. ; Senior Grade School of Computer Science and Engineering (SCOPE), Vellore Institute of Technology, Chennai, Tamilnadu, India

* Corresponding author.

Abstract

In this paper, we introduce an innovative approach that merges linguistic prompting with reinforcement learning to improve the quality of text summarization models. The primary focus is on enhancing the human-centered evaluation of these models, which is crucial for ensuring that the generated summaries are both useful and understandable. Our framework uses linguistic prompts as a guiding tool in the summarization process, providing more precise control over the resulting summaries. This method allows the summarization model to produce outputs that are not only accurate but also reflective of specific human-like cues, such as tone and context. By doing so, we can steer the model's behavior toward generating summaries that are more aligned with human expectations. To further refine the model's performance, we integrate reinforcement learning into our framework. This technique involves iterative improvement based on feedback from human evaluators, allowing the model to learn from its mistakes and continuously adapt to human preferences. This reinforcement-based approach ensures that the summarization model evolves over time, achieving greater accuracy and relevance with each iteration. Our methodology addresses a key challenge in text summarization: creating summaries that are concise yet sufficiently informative. By leveraging linguistic prompting and reinforcement learning, we aim to develop a system that produces summaries that are not only shorter but also more meaningful from a human perspective. This work contributes to the advancement of natural language processing by offering a novel way to balance brevity and informativeness, ultimately leading to more interpretable and human-friendly text summarization tasks.

Keywords

human-centered evaluation; linguistic prompting; natural language processing; reinforcement learning; text summarization

Hrčak ID:

320370

URI

https://hrcak.srce.hr/320370

Publication date:

31.8.2024.

Visits: 476 *