PENGEMBANGAN PROTOTIPE CHATBOT, FINE-TUNING MODEL NLP BERBASIS TRANSFORMER INTEGRASI MODUL SIMBOLIK MATEMATIKA, PENGUJIAN AWAL DAN EVALUASI PERFORMA

  • Trisna Rukhmana STKIP Muhammadiyah Sungai Penuh
  • Al Ikhlas STKIP Muhammadiyah Sungai Penuh
  • Sonya Heswari STKIP Muhammadiyah Sungai Penuh
Keywords: Chatbot, NLP, Transformer, Simbolik Matematika, Integrasi Sistem

Abstract

Penelitian ini bertujuan untuk mengeksplorasi pengembangan prototipe chatbot yang mengintegrasikan model Natural Language Processing (NLP) berbasis transformer dengan modul simbolik matematika. Pendekatan kualitatif digunakan untuk memahami secara mendalam proses integrasi dua teknologi tersebut serta dampaknya terhadap peningkatan akurasi dan konteks jawaban yang diberikan oleh chatbot dalam menangani pertanyaan matematika. Fokus utama penelitian adalah untuk menilai sejauh mana kombinasi pemahaman bahasa alami dan kemampuan pemrosesan simbolik dapat menghasilkan sistem interaktif yang mampu merespons pertanyaan matematika secara tepat dan relevan. Hasil penelitian menunjukkan bahwa integrasi ini memberikan potensi besar dalam mengembangkan chatbot edukatif yang lebih adaptif dan cerdas dalam konteks pembelajaran maupun aplikasi profesional.

References

Allamanis, M., Barr, E. T., Devanbu, P., & Sutton, C. (2018). A Survey of Machine Learning for Big Code and Naturalness. ACM Computing Surveys (CSUR), 51(4), 1–37.
Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., ... & Amodei, D. (2020). Language Models are Few-Shot Learners. Advances in Neural Information Processing Systems, 33, 1877–1901.
Cambria, E., Poria, S., Hazarika, D., & Kwok, K. (2020). SenticNet 6: Ensemble Application of Symbolic and Subsymbolic AI for Sentiment Analysis. Proceedings of the 29th ACM International Conference on Information & Knowledge Management (CIKM), 105–114.
Chen, M., Tworek, J., Jun, H., Yuan, Q., de Oliveira Pinto, H. P., Kaplan, J., ... & Zaremba, W. (2021). Evaluating Large Language Models Trained on Code. arXiv preprint arXiv:2107.03374.
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 4171–4186.
Gao, L., & Lin, T. (2022). Symbolic Knowledge Integration for Explainable AI: A Review. Information Fusion, 83, 146–158.
Jurafsky, D., & Martin, J. H. (2023). Speech and Language Processing (3rd ed.). Draft available at https://web.stanford.edu/~jurafsky/slp3/
Kingma, D. P., & Ba, J. (2015). Adam: A Method for Stochastic Optimization. International Conference on Learning Representations (ICLR). arXiv:1412.6980.
Lample, G., & Charton, F. (2019). Deep Learning for Symbolic Mathematics. arXiv preprint arXiv:1912.01412.
Liang, P., Jordan, M. I., & Klein, D. (2013). Learning Dependency-Based Compositional Semantics. Computational Linguistics, 39(2), 389–446.
Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient Estimation of Word Representations in Vector Space. arXiv preprint arXiv:1301.3781.
Radev, D. R., Muthukrishnan, P., Qazvinian, V., & Abu-Jbara, A. (2009). A Survey of Text Summarization Techniques. In Mining Text Data (pp. 43–76). Springer.
Tenney, I., Das, D., & Pavlick, E. (2019). BERT Rediscovers the Classical NLP Pipeline. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 4593–4601.
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017). Attention is All You Need. Advances in Neural Information Processing Systems, 30, 5998–6008.
Wolfram Research. (2021). Mathematica and the Wolfram Language Documentation. Retrieved from https://www.wolfram.com/language/
Published
2023-12-31
How to Cite
Trisna Rukhmana, Al Ikhlas, & Sonya Heswari. (2023). PENGEMBANGAN PROTOTIPE CHATBOT, FINE-TUNING MODEL NLP BERBASIS TRANSFORMER INTEGRASI MODUL SIMBOLIK MATEMATIKA, PENGUJIAN AWAL DAN EVALUASI PERFORMA . EDU RESEARCH, 4(4), 270-278. https://doi.org/10.47827/jer.v4i4.846
Section
Articles