p-Index From 2020 - 2025
4.926
P-Index
Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : International Journal of Electrical and Computer Engineering

Named entity recognition on Indonesian legal documents: a dataset and study using transformer-based models Yulianti, Evi; Bhary, Naradhipa; Abdurrohman, Jafar; Dwitilas, Fariz Wahyuzan; Nuranti, Eka Qadri; Husin, Husna Sarirah
International Journal of Electrical and Computer Engineering (IJECE) Vol 14, No 5: October 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v14i5.pp5489-5501

Abstract

The large volume of court decision documents in Indonesia poses a challenge for researchers to assist legal practitioners in extracting useful information from the documents. This information can also benefit the general public by improving legal transparency, law enforcement, and people's understanding of the law implementation in Indonesia. A natural language processing task that extracts important information from a document is called named entity recognition (NER). In this study, the NER task is applied to legal domains, which is then referred to as legal entity recognition (LER) task. In this task, some important legal entities, such as judges, prosecutors, and advocates, are extracted from the decision documents. A new Indonesian LER dataset is built, called IndoLER data, consisting of approximately 1K decision documents with 20 types of fine-grained legal entities. Then, the transformer-based models, such as multilingual bidirectional encoder representations from transformers (BERT) or M-BERT, Indonesian BERT or IndoBERT, Indonesian robustly optimized BERT pretraining approach (RoBERTa) or IndoRoBERTa, XLM (cross lingual language model)-RoBERTa or XLMR, are proposed to solve the Indonesian LER task using this dataset. Our experimental results show that the RoBERTa-based models, such as XLM-R and IndoRoBERTa, can outperform the state-of-the-art deep-learning baselines using BiLSTM (bidirectional long short-term memory) and BiLSTM-conditional random field (BiLSTM-CRF) approaches by 7.2% to 7.9% and 2.1% to 2.6%, respectively. XLM-RoBERTa is shown to be the best-performing model, achieving the F1-score of 0.9295.
Co-Authors Abdul Haris Abdurrohman, Jafar Abro, Fikri Adriana, Risda Agung Bambang Setio Utomo Agus Sugandha Ahmad Dahlan Alfina, Ika Alie, M. Fadhiel Aminuddin, Jamrud Anandez, Arum Adisha Putra Annas, Dicky Atmoko, Indri Aulia, Muti’a Rahma A’yun, Nidha Aulia Qurrata Bambang Subeno Berghuis, Nila Tanyela Bhary, Naradhipa Bilalodin Bilalodin Budi, Indra Busral, Busral Coyanda, John Roni Cyndika Dana Indra Sensuse Dari, Qorinah Wulan DEWI SARTIKA Dhamayanti, Dhamayanti Dwitilas, Fariz Wahyuzan Eka Qadri Nuranti Enrique, Gabriel Faradillah Fatari, Fatari Febrianto, Muhamad Rizki Fridarima, Shanny Geni, Lenggo Gupron, Akhmad Hananto, Djoko Haryadi, Arifin Nur Muhammad Hasnawati Hasnawati Hayati, Atika Trisna Heri Jodi, Heri Humairoh, Nayu Nur Husin, Husna Sarirah Imelda Saluza, Imelda Indah Permatasari Iskandar Zulkarnaen Jayawarsa, A.A. Ketut Kartika Sari Khusaenah, Nur Kurniawan, Alfin Lastri Widya Astuti, Lastri Widya Laugiwa, Matiin Lukman Hakim Madiabu, Muhammad Jihad Mannix, Ilma Alpha Marcelina, Dona Martawijaya, M. Agus Meganingrum Arista Jiwanggi Ndruru, Sun Theo Constan Lotebulo Nissa, Nuzulul Khairu Nua, Muh. Tri Prasetia Pisgamargareta, Abel Praktino, Budi Prasetyo, Ridho Pratama, Mochamad Jodi Pratiwi, Indah Putri Putri Rizqiyah Putri, Indah Pratiwi Rabiyatul Adawiyah Siregar Rachmadhanti, Elvira Nur Rachmawati, Nur Rama Samudra, M.S Ramadhan, Mustafa Ridho, Muhammad Yusuf Rohmad Salam, Rohmad Rosiana Dwi Saputri, Rosiana Dwi Sampora, Yulianti Saputra, Muklas Ade Sofyan, Muhammad Ihsan Sudaryanto Sulkiah Hendrawati Sumarsih, Rani Sri Sunardi Sunardi Suryati Syazali, Muhammad Rizki Terttiaavini Terttiavini, Terttiavini Zulham Zulham