Ontology-Based Text Summarization for Marathi Legal Documents

Objectives/Background: Government documents of Maharashtra state are written in Marathi language, and they are long in length, detailed, and difficult to read quickly. There is a requirement to develop a system which will automatically summarize these documents to understand the key information quickly. Therefore, this research aims to create an ontology-based method for summarizing government documents by improving understanding using domain-specific terms and their relationships. Method: This study proposes a novel technique that uses ontology as a knowledge base, which consists of significant concepts associated with a specific subject and their interconnections. It helps the system to understand the content with its meaning. With this understanding, the algorithm selects important information and generates summaries that maintain the clarity and importance of the text. Findings: The proposed method achieves Precision of 0.82, ROUGE-1 score of 0.85, and ROUGE-2 score of 0.78. These results show that the summaries are accurate, meaningful and match the reference summaries. The proposed system may also reduce the effort required to read long documents by generating short and meaningful summaries. It improves both the quality and reliability of text summarization and works well for domain-specific applications where meaningful summaries are important. Novelty: This research work is different from the traditional statistical text summarization techniques as it uses the ontology to capture text relationships resulting in an improved context understanding and accurate summaries. Keywords: Text Summarization, Ontology-based, Domain knowledge, Marathi Language, Administrative documents