Medical Named Entity Recognition from Indonesian Health-News using BiLSTM-CRF with Static and Contextual Embeddings
DOI:
https://doi.org/10.30871/jaic.v9i6.11574Keywords:
Named Entity Recognition, Medical Entity, Word2Vec, IndoBERT, Indonesian Health NewsAbstract
Named Entity Recognition (NER) is vital for structuring medical texts by identifying entities such as diseases, symptoms, and drugs. However, research on Indonesian medical NER remain limited due to the lack of annotated corpora and linguistic resources. This scarcity often leads to difficulties in learning meaningful word representations, which are crucial for accurate entity identification. This research aims to compare the effectiveness of static and contextual embeddings in enhancing entity recognition on Indonesian biomedical text. The experimental setup involved utilizing both static (Word2Vec) and contextual (IndoBERT) embeddings in conjunction with neural architectures (BiLSTM) along with Conditional Random Fields (CRF). The BiLSTM architecture was selected for its ability to capture bidirectional dependencies in language sequences. Specifically, four models: Word2Vec-BiLSTM, Word2Vec-BiLSTM-CRF, IndoBERT-BiLSTM, and IndoBERT-BiLSTM-CRF were evaluated to assess the impact of contextual representations and structured decoding. The models were trained on a manually annotated DetikHealth corpus, where specific medical entities such as diseases, symptoms, and drugs were labeled with the BIO-tagging scheme. Performance was subsequently evaluated based on standard metrics: precision, recall, and F1-score. Results indicate that IndoBERT’s contextual embeddings significantly outperform static Word2Vec features. The IndoBERT-BiLSTM-CRF model achieved the highest performance micro-F1 0.4330, macro-F1 0.3297, with the Disease entity reaching an F1-score of 0.5882. Combining contextual embeddings with CRF-based decoding enhances semantic understanding and boundary consistency, demonstrating superior performance for Indonesian biomedical NER. Future work should explore domain-adaptive pretraining and larger biomedical corpora to further improve contextual accuracy.
Downloads
References
[1] K. Pakhale, “Comprehensive Overview of Named Entity Recognition: Models, Domain-Specific Applications and Challenges,” Sept. 25, 2023, arXiv: arXiv:2309.14084. doi: 10.48550/arXiv.2309.14084.
[2] S. Liu, Y. Sun, B. Li, W. Wang, and X. Zhao, “HAMNER: Headword Amplified Multi-Span Distantly Supervised Method for Domain Specific Named Entity Recognition,” Proc. AAAI Conf. Artif. Intell., vol. 34, no. 05, pp. 8401–8408, Apr. 2020, doi: 10.1609/aaai.v34i05.6358.
[3] R. Zhang, Y. Shan, and M. Zhen, “Advancing named entity recognition in interprofessional collaboration and education,” Front. Med., vol. 12, p. 1578769, June 2025, doi: 10.3389/fmed.2025.1578769.
[4] W. Khan, A. Daud, K. Shahzad, T. Amjad, A. Banjar, and H. Fasihuddin, “Named Entity Recognition Using Conditional Random Fields,” Appl. Sci., vol. 12, no. 13, p. 6391, Jan. 2022, doi: 10.3390/app12136391.
[5] J. Li, A. Sun, J. Han, and C. Li, “A Survey on Deep Learning for Named Entity Recognition,” IEEE Trans. Knowl. Data Eng., vol. 34, no. 1, pp. 50–70, Jan. 2022, doi: 10.1109/TKDE.2020.2981314.
[6] A. Khalid, G. Mustafa, M. R. R. Rana, S. M. Alshahrani, and M. Alymani, “RNN-BiLSTM-CRF based amalgamated deep learning model for electricity theft detection to secure smart grids,” PeerJ Comput. Sci., vol. 10, p. e1872, Feb. 2024, doi: 10.7717/peerj-cs.1872.
[7] R. Phukan, N. Baruah, M. Neog, S. KR. Sarma, and D. Konwar, “A Hybrid Neural-CRF Framework for Assamese Part-of-Speech Tagging,” IEEE Access, vol. 13, pp. 160476–160489, 2025, doi: 10.1109/ACCESS.2025.3609572.
[8] J. Hou, S. Saad, and N. Omar, “Enhancing traditional Chinese medical named entity recognition with Dyn-Att Net: a dynamic attention approach,” PeerJ Comput. Sci., vol. 10, p. e2022, May 2024, doi: 10.7717/peerj-cs.2022.
[9] K. Kugler, S. Münker, J. Höhmann, and A. Rettinger, “InvBERT: Reconstructing Text from Contextualized Word Embeddings by inverting the BERT pipeline,” Mar. 2024, doi: 10.48694/jcls.3572.
[10] Q. Qin, S. Zhao, and C. Liu, “A BERT‐BiGRU‐CRF Model for Entity Recognition of Chinese Electronic Medical Records,” Complexity, vol. 2021, no. 1, p. 6631837, Jan. 2021, doi: 10.1155/2021/6631837.
[11] M. Tu, “Named entity recognition and emotional viewpoint monitoring in online news using artificial intelligence,” PeerJ Comput. Sci., vol. 10, p. e1715, 2024, doi: 10.7717/peerj-cs.1715.
[12] M. Kurniawan and B. Juarto, “Unlocking the Potential of IndoBERT for Classification of Indonesian Thesis,” in 2024 International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS), Nov. 2024, pp. 785–791. doi: 10.1109/ICIMCIS63449.2024.10956541.
[13] F. Koto, A. Rahimi, J. H. Lau, and T. Baldwin, “IndoLEM and IndoBERT: A Benchmark Dataset and Pre-trained Language Model for Indonesian NLP,” Nov. 02, 2020, arXiv: arXiv:2011.00677. doi: 10.48550/arXiv.2011.00677.
[14] W. Wongso, D. S. Setiawan, S. Limcorn, and A. Joyoadikusumo, “NusaBERT: Teaching IndoBERT to be Multilingual and Multicultural,” Mar. 04, 2024, arXiv: arXiv:2403.01817. doi: 10.48550/arXiv.2403.01817.
[15] F. Koto, J. H. Lau, and T. Baldwin, “IndoBERTweet: A Pretrained Language Model for Indonesian Twitter with Effective Domain-Specific Vocabulary Initialization,” Sept. 10, 2021, arXiv: arXiv:2109.04607. doi: 10.48550/arXiv.2109.04607.
[16] Warto, Muljono, Purwanto, and E. Noersasongko, “Improving Named Entity Recognition in Bahasa Indonesia with Transformer-Word2Vec-CNN-Attention Model.,” Int. J. Intell. Eng. Syst., vol. 16, no. 4, p. 655, July 2023, doi: 10.22266/ijies2023.0831.53.
[17] E. Dave and A. Chowanda, “IPerFEX-2023: Indonesian personal financial entity extraction using indoBERT-BiGRU-CRF model,” J. Big Data, vol. 11, no. 1, p. 139, Sept. 2024, doi: 10.1186/s40537-024-00987-6.
[18] J. R. Dettori and D. C. Norvell, “Kappa and Beyond: Is There Agreement?,” Glob. Spine J., vol. 10, no. 4, pp. 499–501, June 2020, doi: 10.1177/2192568220911648.
[19] K. Smelyakov, D. Karachevtsev, D. Kulemza, Y. Samoilenko, O. Patlan, and A. Chupryna, “Effectiveness of Preprocessing Algorithms for Natural Language Processing Applications,” in 2020 IEEE International Conference on Problems of Infocommunications. Science and Technology (PIC S&T), Kharkiv, Ukraine: IEEE, Oct. 2020, pp. 187–191. doi: 10.1109/PICST51311.2020.9467919.
[20] Nurul Hannah Mohd Yusof, Nurul Adilla Mohd Subha, Nurulaqilla Khamis, and Norikhwan Hamzah, “Named Entity Recognition of an Oversampled and Preprocessed Manufacturing Data Corpus,” J. Adv. Res. Appl. Sci. Eng. Technol., vol. 36, no. 1, pp. 203–216, Dec. 2023, doi: 10.37934/araset.36.1.203216.
[21] H. R. Maier et al., “On how data are partitioned in model development and evaluation: Confronting the elephant in the room to enhance model generalization,” Environ. Model. Softw., vol. 167, p. 105779, Sept. 2023, doi: 10.1016/j.envsoft.2023.105779.
[22] Q. Chen and M. Sokolova, “Specialists, Scientists, and Sentiments: Word2Vec and Doc2Vec in Analysis of Scientific and Medical Texts,” SN Comput. Sci., vol. 2, no. 5, p. 414, Aug. 2021, doi: 10.1007/s42979-021-00807-1.
[23] S. Sun, Q. Hu, F. Xu, F. Hu, Y. Wu, and B. Wang, “Medical named entity recognition based on domain knowledge and position encoding,” BMC Med. Inform. Decis. Mak., vol. 25, p. 235, July 2025, doi: 10.1186/s12911-025-03037-0.
[24] X. Zhang et al., “Chinese medical named entity recognition integrating adversarial training and feature enhancement,” Sci. Rep., vol. 15, no. 1, p. 14844, Apr. 2025, doi: 10.1038/s41598-025-98465-3.
[25] C. J. Pinard, A. C. Poon, A. Lagree, K.-C. Wu, J. Li, and W. T. Tran, “Precision in Parsing: Evaluation of an Open-Source Named Entity Recognizer (NER) in Veterinary Oncology,” Vet. Comp. Oncol., vol. 23, no. 1, pp. 102–108, 2025, doi: 10.1111/vco.13035.
[26] T. Nguyen, D. Nguyen, and P. Rao, “Adaptive Name Entity Recognition under Highly Unbalanced Data,” Mar. 10, 2020, arXiv: arXiv:2003.10296. doi: 10.48550/arXiv.2003.10296.
[27] A. Srinivasan and S. Vajjala, “A Multilingual Evaluation of NER Robustness to Adversarial Inputs,” May 30, 2023, arXiv: arXiv:2305.18933. doi: 10.48550/arXiv.2305.18933.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Darnell Ignasius, Ika Novita Dewi , Maria Bernadette Chayeenee Norman , Ramadhan Rakhmat Sani
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
