Abstract
Current conversational agents are primarily designed to answer user queries based on structured pre-defined utterance-response pairs. While question-answering (QA) systems extracts potential answers, to queries, from unstructured texts. However, in domain-specific settings, manual creation of query-response pairs is expensive, and domain adaptation of QA platforms is crucial. To this end, we propose Cage, a “hybrid” conversational framework seamlessly integrating structured and unstructured data to obtain precise answers for user queries – improving user experience and quality-of-service. We describe the different components combining query matching and extractive question answering, and demonstrate the multi-lingual chatbot interface provided to a user.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Adamopoulou, E., Moussiades, L.: An overview of chatbot technology. In: AIAI, pp. 373–383 (2020)
Assem, H., Sarkar, R., Dutta, S.: QASAR: self-supervised learning framework for extractive question answering. In: IEEE Big Data, pp. 1797–1808 (2021)
Bocklisch, T., Faulkner, J., Pawlowski, N., Nichol, A.: Rasa: open source language understanding and dialogue management. In: NIPS Workshop on Conversational AI (2017)
Gapanyuk, Y., Chernobrovkin, S., Leontiev, A., Latkin, I., Belyanova, M., Morozenkov, O.: A hybrid chatbot system combining QA and knowledge-base approaches. In: AIST (2018)
Hussain, S., Sianaki, O., Ababneh, N.: A survey on conversational agents/chatbots classification and design techniques. In: Barolli, L., Takizawa, M., Xhafa, F., Enokido, T. (eds.) Web, Artificial Intelligence and Network Applications. WAINA 2019. AISC, vol. 927, pp. 946–956. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-15035-8_93
Manzano, M.D.I., Lopez, N.V., Gonzalez, N.A., Rodriguez, C.C.: Implementation of chatbot in online commerce, and open innovations. J. Open Innov. Tech. Market Complx. 7(2) (2021)
Joshi, M., Chen, D., Liu, Y., Weld, D.S., Zettlemoyer, L., Levy, O.: Spanbert: improving pre-training by representing and predicting spans. TACL 8, 64–77 (2020)
Jovanovic, M., Baez, M., Casati, F.: Chatbots as conversational healthcare services. IEEE Internet Comput. 25(3), 44–51 (2021)
Lommatzsch, A., Katins, J.: An information retrieval-based approach for building intuitive chatbots for large knowledge bases. In: LWDA (2019)
McTear, M.: Conversational AI: Dialogue Systems. Conversational Agents and Chatbots, Morgan and Claypool (2021)
Patel, R.N., Burgin, E., Assem, H., Dutta, S.: Efficient multi-lingual sentence classification framework with sentence meta encoders. In: IEEE Big Data, pp. 1889–1899 (2021)
Raffel, C., et al.: Exploring the limits of transfer learning with a unified t2t transformer. arXiv:1910.10683 (2019)
Yan, Z., et al.: DocChat: an IR approach for chatbot engines using unstructured documents. In: ACL, pp. 516–525 (2016)
Zhang, Z., Zhao, H., Wang, R.: Machine reading comprehension: the role of contextualized language models and beyond. Comput. Linguist. 1(1), 1–51 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Burgin, E., Dutta, S., Assem, H., Patel, R.N. (2023). Cage: A Hybrid Framework for Closed-Domain Conversational Agents. In: Amini, MR., Canu, S., Fischer, A., Guns, T., Kralj Novak, P., Tsoumakas, G. (eds) Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2022. Lecture Notes in Computer Science(), vol 13718. Springer, Cham. https://doi.org/10.1007/978-3-031-26422-1_46
Download citation
DOI: https://doi.org/10.1007/978-3-031-26422-1_46
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-26421-4
Online ISBN: 978-3-031-26422-1
eBook Packages: Computer ScienceComputer Science (R0)
