Academic Journal of Computing & Information Science, 2024, 7(11); doi: 10.25236/AJCIS.2024.071101.
Siyi Wu1, Weizhi Luo2, Zihao Wang2, Junxi Li3
1Nanjing University of Science and Technology, Nanjing, China
2Peter the Great St. Petersburg Polytechnic University, Saint Petersburg, Russia
3Herzen University, Saint Petersburg, Russia
During the development of chatbot technology, we are faced with the challenge of how to improve the interaction capability and user experience of bots. As technology continues to advance, we propose novel architectures that combine retrieval-based chatbots and generative chatbots, aiming to improve the interaction capability and user experience of chatbots. Retrieval-based bots rely on an existing knowledge base to answer questions, while generative bots can generate coherent dialogues. Combining the advantages of both, retrieval-based bots can quickly find information and then use generative bots to generate more natural dialogue. Experiments show that this architecture greatly improves the interaction capabilities and user satisfaction of chatbots.
Retrieval Robot; Generative Chatbot; Generative Network; Attention Mechanism
Siyi Wu, Weizhi Luo, Zihao Wang, Junxi Li. Research on Adaptive Dialogue Strategies Combining Retrieval and Generative Chatbots. Academic Journal of Computing & Information Science (2024), Vol. 7, Issue 11: 1-8. https://doi.org/10.25236/AJCIS.2024.071101.
[1] Wang Z,Chen A,Tao K, et al. MatGPT: A Vane of Materials Informatics from Past, Present, to Future [J]. Adv Mater. 2024;36 (6):e2306733. doi:10.1002/adma.202306733
[2] Luo L,Ogawa K,Peebles G, et al. Towards a Personality AI for Robots: Potential Colony Capacity of a Goal-Shaped Generative Personality Model When Used for Expressing Personalities via Non-Verbal Behaviour of Humanoid Robots [J]. Front Robot AI. 2022; 9:728776. doi:10.3389/frobt.2022. 728776
[3] Borges, R.M. A Braver New World? Of chatbots and other cognoscenti [J]. J Biosci, 2023, 48, 10. https://doi.org/10.1007/s12038-023-00334-6
[4] Nishimura Y,Nakamura Y,Ishiguro H. Human interaction behavior modeling using Generative Adversarial Networks [J]. Neural Netw. 2020;132:521-531. doi:10.1016/j.neunet.2020.09.019
[5] Prescott TJ,Camilleri D,Martinez-Hernandez U, et al. Memory and mental time travel in humans and social robots [J]. Philos Trans R Soc Lond B Biol Sci. 2019; 374 (1771):20180025. doi:10.1098/rstb. 2018. 0025
[6] Rizvi SKJ, Azad MA,Fraz MM. Spectrum of Advancements and Developments in Multidisciplinary Domains for Generative Adversarial Networks (GANs) [J]. Arch Comput Methods Eng. 2021;28 (7):4503-4521. doi:10.1007/s11831-021-09543-4
[7] Lowe R, Pow N, Serban I, et al.The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems[C] // Proceedings of the SIGDIAL 2015 Conference, The 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue. Prague, Czech Republic, 2015: 285 - 294.
[8] ZHANG S, DINAN E, URBANEK J, et al. Personalizing Dialogue Agents: I have a dog, do you have pets too? [C] // Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics. ACL, 2018 : 2204-2213.
[9] WELLECK S, WESTON J, SZLAM A, et al. Dialogue natural language inference [C] // Proceedings of the57th Annual Meeting of the Association for Computational Linguistics.ACL, 2019 : 3731-3741.
[10] WU Y, WU W, XING C, et al. Sequential Match Network: A New Architecture for Multi-turn Response Selection in Retrieval-based Chatbots [C] // Proceedings of the 55th Annual Mee-ting of the Association for Computational Linguistics. 2017 : 496-505.
[11] Zupanc K, Štrumbelj E. A Bayesian hierarchical latent trait model for estimating rater bias and reliability in large-scale performance assessment [J]. PLoS One. 2018;13 (4):e0195297. doi:10.1371/ journal. pone.0195297.
[12] Yu L, Zhang W, Wang J et al. Seqgan: sequence generative adversarial nets with policy gradient [C]. In: Proceedings of the AAAI conference on artificial intelligence, 2017.