Implementasi LexRank dan BERT2GPT dalam Auto Summarization Teks Bahasa Indonesia

Abstract

In Indonesia, with the rapid growth of internet and social media usage, the amount of information produced in the Indonesian language has reached significant levels. This creates challenges in managing and understanding this information quickly and efficiently. Text summarization has emerged as a potential solution to help users organize and summarize information, enabling easier and more efficient access to relevant content. This study discusses the development of an Indonesian text summarization model using the LexRank algorithm. The results show that this model can produce accurate and concise summaries, with ROUGE-L result of 0.91 and also a ROUGE-1 result of 0.31. Developing an Indonesian text summarization model is important because it can help users manage and understand information quickly and efficiently. This study provides a positive contribution to the development of Indonesian text summarization models, by providing evidence that the LexRank model can produce accurate and concise summaries.