Document Type : Applied Article

Authors

• Mohammad Aalishahi ¹
• Mohammad Hadi Bokaei ²
• Abolfazl Nadi ³

¹ Instructor, Department of Computer Science, Kish International Campus, University of Tehran, Kish, Iran

² ICT Research Institute Tehran, Iran.

³ Computer Science, Tehran, Kish, Iran

Abstract

Given the importance of Named Entity Recognition (NER), numerous studies have been conducted in this field. However, most research has focused on languages such as English, French, and Arabic. In contrast, studies on Persian remain limited, despite Persian being one of the most widely spoken languages in West Asia, necessitating the development of NER methods for it. In this study, using Active Learning, a corpus of 1,351 advertisements from the Official Gazette was annotated. The GEMMA2b model was then fine-tuned on this data, achieving approximately 95% accuracy. This model was employed to extract around 13 types of named entities and their relationships within the advertisement texts. The primary advantage of this method is the model’s high accuracy compared to other approaches. Additionally, the use of Persian data—which, unlike languages such as English or Arabic, has fewer resources—is another notable feature of this research.

Keywords

• Named Entity Recognition
• Natural Language Processing
• LLM
• Multi Agent System
• Persian Language LoRA

Main Subjects

• H.3. Artificial Intelligence