Pembangkitan Respons pada Model Seq2seq Chatbot Berbahasa Indonesia dengan Multimodal Learning (Intensi dan Entitas)
Kata Kunci:
chatbot, multimodal learning, Seq2seq Model, Seq2seq Modality Translation Model, LSTMAbstrak
Helpdesk TIK UB adalah layanan helpdesk daring untuk membantu menyelesaikan permasalahan mengenai teknologi informasi di Universitas Brawijaya (UB). Helpdesk TIK UB dapat digunakan oleh seluruh civitas academica Universitas Brawijaya. Pelayanan Helpdesk TIK UB tersedia selama hari dan jam kerja, sehingga permasalahan yang mendesak di luar jam kerja tidak langsung dilayani. Salah satu bentuk teknologi yang dapat menyelesaikan permasalahan tersebut adalah penerapan chatbot pada Helpdesk TIK UB. Salah satu model chatbot adalah Sequence to Sequence (Seq2seq) Model yang dikembangkan oleh Sutskever, Vinyals, dan Le pada tahun 2014. Permasalahan yang ditemukan dari Seq2seq Model adalah model ini lebih berfokus pada generasi kata serta kurang memperhitungkan maksud dan konteks dari pengguna (Mustapha et al., 2008; Vinyals and Le, 2015; Dudy, Bedrick and Webber, 2021). Penelitian ini berupaya untuk mengatasi masalah tersebut dengan menambahkan modalitas intensi dan entitas serta menerapkan multimodal learning menggunakan Seq2seq Modality Translation Model. Hasil dari penelitian ini adalah penggunaan multimodal learning dengan modalitas intensi dan entitas membuat BLEU Score yang dihasilkan model menurun. Namun, kombinasi multimodal yang tepat justru dapat membuat model menangkap konteks kalimat lebih tepat sehingga dapat menghasilkan keluaran yang lebih baik. Hasil penelitian ini menunjukkan bahwa multimodal learning dengan modalitas intensi dan entitas dapat diterapkan pada pembangkitan respons model Seq2seq chatbot berbahasa Indonesia.
Referensi
Adamopoulou, E. and Moussiades, L., 2020. An Overview of Chatbot Technology. In: IFIP Advances in Information and Communication Technology. https://doi.org/10.1007/978-3-030-49186-4_31.
Annisa, Z.A., Perdana, R.S. and Adikara, P.P., 2023. Kombinasi Intent Classification dan Named Entity Recognition pada Data Berbahasa Indonesia dengan Metode Dual Intent and Entity Transformer. Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, 7(13).
Cahn, J., 2017. Chatbot: architecture, design & development. Scientific Reports, 19(1).
Dudy, S., Bedrick, S. and Webber, B., 2021. Refocusing on Relevance: Personalization in NLG. In: EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing, Proceedings. https://doi.org/10.18653/v1/2021.emnlp-main.421.
Gillis, A.S., 2023. Natural Language Understanding (NLU). [online] Available at: <https://www.techtarget.com/searchenterpriseai/definition/natural-language-understanding-NLU> [Accessed 16 October 2023].
Helpdesk TIK, 2023. Helpdesk TIK. [online] Available at: <https://helpdesk-tik.ub.ac.id/> [Accessed 16 October 2023].
Mustapha, A., Md Nasir, S., Mahmod, R. and Selamat, H., 2008. Classification-and-ranking architecture for response generation based on intentions. International Journal of Computer Science and Network Security, 8(12), pp.253–258.
Pham, H., Manzini, T., Liang, P.P. and Poczós, B., 2019. Seq2Seq2Sentiment: Multimodal Sequence to Sequence Models for Sentiment Analysis. https://doi.org/10.18653/v1/w18-3308.
Poulinakis, K., 2022. Multimodal Deep Learning: Definition, Examples, Applications. [online] Available at: <https://www.v7labs.com/blog/multimodal-deep-learning-guide> [Accessed 16 October 2023].
Setijaningrum, E., 2009. Inovasi Pelayanan Publik. 1st ed. Surabayan: PT. Medika Aksara Globalindo.
Sojasingarayar, A., 2020. Seq2Seq AI Chatbot with Attention Mechanism.
Tseng, B.H., Cheng, J., Fang, Y. and Vandyke, D., 2020. A generative model for joint natural language understanding and generation. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics. https://doi.org/10.18653/v1/2020.acl-main.163.
Vajjala, S., Majumder, B., Gupta, A. and Surana, H., 2020. Practical Natural Language Processing: A Comprehensive Guide to Building Real-World NLP Systems. O’Reilly, .
Vinyals, O. and Le, Q., 2015. A Neural Conversational Model.
Wigmore, I., 2023. Natural Language Generation (NLG). [online] Available at: <https://www.techtarget.com/searchenterpriseai/definition/natural-language-generation-NLG> [Accessed 16 October 2023].
Adamopoulou, E. and Moussiades, L., 2020. An Overview of Chatbot Technology. In: IFIP Advances in Information and Communication Technology. https://doi.org/10.1007/978-3-030-49186-4_31.
Annisa, Z.A., Perdana, R.S. and Adikara, P.P., 2023. Kombinasi Intent Classification dan Named Entity Recognition pada Data Berbahasa Indonesia dengan Metode Dual Intent and Entity Transformer. Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, 7(13).
Cahn, J., 2017. Chatbot: architecture, design & development. Scientific Reports, 19(1).
Dudy, S., Bedrick, S. and Webber, B., 2021. Refocusing on Relevance: Personalization in NLG. In: EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing, Proceedings. https://doi.org/10.18653/v1/2021.emnlp-main.421.
Gillis, A.S., 2023. Natural Language Understanding (NLU). [online] Available at: <https://www.techtarget.com/searchenterpriseai/definition/natural-language-understanding-NLU> [Accessed 16 October 2023].
Helpdesk TIK, 2023. Helpdesk TIK. [online] Available at: <https://helpdesk-tik.ub.ac.id/> [Accessed 16 October 2023].
Mustapha, A., Md Nasir, S., Mahmod, R. and Selamat, H., 2008. Classification-and-ranking architecture for response generation based on intentions. International Journal of Computer Science and Network Security, 8(12), pp.253–258.
Pham, H., Manzini, T., Liang, P.P. and Poczós, B., 2019. Seq2Seq2Sentiment: Multimodal Sequence to Sequence Models for Sentiment Analysis. https://doi.org/10.18653/v1/w18-3308.
Poulinakis, K., 2022. Multimodal Deep Learning: Definition, Examples, Applications. [online] Available at: <https://www.v7labs.com/blog/multimodal-deep-learning-guide> [Accessed 16 October 2023].
Setijaningrum, E., 2009. Inovasi Pelayanan Publik. 1st ed. Surabayan: PT. Medika Aksara Globalindo.
Sojasingarayar, A., 2020. Seq2Seq AI Chatbot with Attention Mechanism.
Tseng, B.H., Cheng, J., Fang, Y. and Vandyke, D., 2020. A generative model for joint natural language understanding and generation. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics. https://doi.org/10.18653/v1/2020.acl-main.163.
Vajjala, S., Majumder, B., Gupta, A. and Surana, H., 2020. Practical Natural Language Processing: A Comprehensive Guide to Building Real-World NLP Systems. O’Reilly, .
Vinyals, O. and Le, Q., 2015. A Neural Conversational Model.
Wigmore, I., 2023. Natural Language Generation (NLG). [online] Available at: <https://www.techtarget.com/searchenterpriseai/definition/natural-language-generation-NLG> [Accessed 16 October 2023].
Unduhan
Diterbitkan
Cara Mengutip
Terbitan
Bagian
Lisensi
Hak Cipta (c) 2024 Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Artikel ini berlisensiCreative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.