Design and Implementation of an Intelligent Learning Platform Integrated with Artificial Intelligence
In recent years, large language models (LLMs) such as T5, BART, and GPT have demonstrated significant effectiveness in natural language processing (NLP) tasks, including summarization and question generation. While these models have achieved promising results in various educational applications, mos...
Tallennettuna:
| Päätekijä: | |
|---|---|
| Aineistotyyppi: | Conference paper |
| Kieli: | Vietnamese |
| Julkaistu: |
Nhà xuất bản Khoa học Kỹ thuật
2025
|
| Linkit: | https://scholar.dlu.edu.vn/handle/123456789/4976 |
| Tagit: |
Lisää tagi
Ei tageja, Lisää ensimmäinen tagi!
|
| Thư viện lưu trữ: | Thư viện Trường Đại học Đà Lạt |
|---|
| Yhteenveto: | In recent years, large language models (LLMs) such as T5, BART, and GPT have demonstrated significant effectiveness in natural language processing (NLP) tasks, including summarization and question generation. While these models have achieved promising results in various educational applications, most implementations rely on high-performance infrastructures and large-scale datasets, limiting their accessibility for institutions with constrained resources. This study proposes the development of a lightweight AI-powered learning platform capable of automatic summarization and question-answer generation. We select and train three compact NLP models (T5-small, T5-base, and BART) on a limited dataset and evaluate them under resource-constrained environments. The trained models are then integrated into a web-based learning platform to facilitate interactive educational experiences. Our approach aims to balance output quality and computational efficiency, making AI-enhanced learning accessible for small educational units and individual learners. |
|---|