Sistem Question Answering pada Data Kesehatan Menggunakan Model pre-trained BERT
Abstrak
Setelah pandemi covid-19, kesehatan menjadi hal yang harus diperhatikan. Sebagian besar masyarakat menggunakan search engine sebagai alat untuk mencari informasi tentang kesehatan. Namun informasi yang didapatkan berupa query hasil search engine yang masih umum. Sistem Question Answering adalah sistem yang memberikan informasi sesuai informasi yang dibutuhkan oleh pengguna secara spesifik. Pada penelitian ini dibangun sistem Question Answering menggunakan metode Bidirectional Encoder Representations from Transformer (BERT). BERT merupakan sebuah pre-trained model yang menggunakan arsitektur transformer. BERT dapat menyelesaikan tugas sistem Question Answering. Dengan pre-trained model, sistem tidak perlu melakukan training model dari awal. Sistem hanya perlu menggunakan train model yang telah dibuat oleh orang lain sesuai tugas yang dibutuhkan untuk menghemat waktu dan sumber daya. Untuk mengukur performansi, digunakan metode Exact Match (EM) dan F1-score. Hasil dari penelitian ini skor terbaik yang didapat yaitu Exact Match 75% dan F1-score 76%. Kata kunci— question answering, BERT, pre-trained model, kesehatan
Referensi
K. A. Rizqo, "Resmi! Jokowi Umumkan Status Pandemi COVID-19 Dicabut," detikNews, 21 Juni [Online]. Available: https://news.detik.com/berita/d-6784804/resmijokowi-umumkan-status-pandemi-covid-19-dicabut. [Accessed 6 Januari 2025].
L. N. Hakim, "DAMPAK PANDEMI WABAH CORONAVIRUS DISEASE (COVID) 19 DAN LOCKDOWN TERHADAP KESEHATAN MENTAL: KAJIAN PSIKOLOGI DAN AGAMA," Kajian, vol. 25, no. 2, pp. 161-177, 2020.
A. Sixsmith, B. R. Horst, D. Simeonov and A. Mihailidis, "Older People’s Use of Digital Technology During the COVID-19 Pandemic," Bulletin of Science, Technology & Society, vol. 42, no. 1-2, pp. 19-24, 2022.
D. Vargo, L. Zhu, B. Benwell and Z. Yan, "Digital technology use during COVID-19 pandemic: A rapid review," Human Behavior and Emerging Technologies, vol. 3, no. 3, pp. 13-24, 2020.
J. Moudy and R. A. Syakurah, "Pengetahuan terkait Usaha Pencegahan Coronavirus Disease (COVID19) di Indonesia," HIGEIA JOURNAL OF PUBLIC HEALTH RESEARCH AND DEVELOPMENT, vol. , no. 2, pp. 333-346, 2020.
F. Zhu, W. Lei, J. Zheng, S. Poria and T.-S. Chua, "Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering," arXiv,
J. Devlin, M.-W. Chang, K. Lee and K. Toutanova, "BERT: Pre-training of Deep Bidirectional
Transformers for Language Understanding," 2018.
F. Koto, A. Rahimi, J. H. Lau and T. Baldwin, "IndoLEM and IndoBERT: A Benchmark Dataset and Pre-trained Language Model for Indonesian
NLP," in COLING 2020 - The 28th International Conference on Computational Linguistics, 2020.
F. Dartiko, M. Yusa, A. Erlansari and S. A. Basha, "Comparative Analysis of Transformer-Based
Method In A Question Answering System for Campus Orientation Guides," INTENSIF: Jurnal Ilmiah Penelitian dan Penerapan Teknologi Sistem
Informasi, vol. 8, no. 1, pp. 126-143, 2024.
S. P. Widodo, "Comparative Analysis of Retriever and Reader for Open Domain Questions Answering on BPS Knowledge in Indonesian," Proceedings of The International Conference on Data Science and Official Statistics, vol. 2023, no. 1, pp. 337-343,
J. Bulian, C. Buck, W. Gajewski, B. Boerschinger and T. Schuster, "Tomayto, Tomahto. Beyond Token-level Answer Equivalence for Question Answering Evaluation," 2022.
R. Alqifari, "Question Answering Systems Approaches and Challenges," in Proceedings of the Student Research Workshop Associated with RANLP 2019, 2019.
B. S. Bhatt and H. A. Pandya, "Question Answering Survey: Directions, Challenges, Datasets, Evaluation," 2021.
A. Rogers, O. Kovalera and A. Rumshisky, "A Primer in BERTology: What We Know About How
BERT Works," Transactions of the Association for Computational Linguistics, vol. 8, pp. 842-866, D. Grießhaber, J. Maucher and N. T. Vu, "Finetuning BERT for Low-Resource Natural Language
Understanding," in Proceedings of the 28th International Conference on Computational Linguistics (COLING 2020), Barcelona, 2020.
