Abstract
Artificial Intelligence (AI) is one of the most emerging technologies of the past decade, leading the way towards human and machine interactions in terms of efficiency, accuracy and the overall value gained. This paper describes an intent-lean AI chatbot solution that handles user queries posed in natural language upon business related documents of a single-domain of Hellenic Telecommunications Organization S.A. (HTO). Unlike other traditional chatbot solutions that strictly rely on intent identification, our approach infers the implicit user need in order to provide the most relative documents and text snippets within, as the proper answer. To do this, we proceeded with a custom implementation based on Elasticsearch engine and most common NLP techniques tailored to our needs; i.e., tokenization, lowercase filtering, stop words removal, stemming, fuzzy searching, synonyms, etc. The main challenges as well as the architectural models that thrive to overcome them are being described in detail. Finally, the effectiveness of the proposed solution is being measured and the identified features for improvement are being presented.
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
Notes
- 1.
ELK stands for three open source projects: Elasticsearch, Logstash, and Kibana.
- 2.
60% threshold has been chosen after experimentation with the test questions at hand.
- 3.
Documents not related to the Procurement & Finance domain in scope.
References
Business Process Model and Notation (BPMN) Homepage. https://www.bpmn.org/
Elasticsearch Homepage. https://www.elastic.co/what-is/elasticsearch
Carter, D.: How real is the impact of artificial intelligence. Bus. Inf. Rev. (Bus. Inf. Surv.) 35(3), 99–115 (2018)
Bank of America: Bank of America’s Erica®Surpasses 10 Million Users (2019). https://newsroom.bankofamerica.com/press-releases/consumer-banking/bank-americas-ericar-surpasses-10-million-users-introduces-new
López, G., Quesada, L., et al.: Alexa vs. Siri vs. Cortana vs. Google Assistant: a comparison of speech-based natural user interfaces. In: Nunes, I. (ed.) AHFE 2017. AISC, vol. 592, pp. 241–250. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-60366-7_23
Kerly, A., Hall, P.D., Bull, S.: Bringing chatbots into education: towards natural language negotiation of open learner models. In: International Conference on Innovative Techniques and Applications of Artificial Intelligence, pp. 179–192 (2006). https://doi.org/10.1007/978-1-84628-666-7_14
Oh, K.-J., Lee, D., Ko, B.: A chatbot for psychiatric counseling in mental healthcare service based on emotional dialogue analysis and sentence generation. In: 18th IEEE International Conference on Mobile Data Management MDM (2017). https://doi.org/10.1109/MDM.2017.64
Ngai, E.W.T., Lee, M.C.M., et al.: An intelligent knowledge-based chatbot for customer service. Electron. Commerce Res. Appl. (2021). https://doi.org/10.1016/j.elerap.2021.101098
Hussain, S., Sianaki, O.A., Ababneh, N.: A survey on conversational agents/chatbots classification and design techniques. Artif. Intell. Netw. Appli. Proc. 946–956 (2019). https://doi.org/10.1007/978-3-030-15035-8_93
Skroutz Greek Stemmer Homepage. https://github.com/skroutz/greek_stemmer/blob/master/README.md
Cutting, D., Pedersen, J.: Optimization for dynamic inverted index maintenance. In: Proceedings, pp. 405–411 (1980). https://doi.org/10.1145/96749.98245
Kang, Y., Cai, Z., et al.: Natural language processing (NLP) in management research: a literature review. J. Manag. Anal. 139–172 (2020). https://doi.org/10.1080/23270012.2020.1756939
ELK Stack Homepage. https://www.elastic.co/what-is/elk-stack
Siahaan, A.P.U., Aryza, A., et al.: Combination of Levenshtein distance and Rabin-Karp to improve the accuracy of document equivalence level. Int. J. Eng. Technol. 7, 17–21 (2018). http://dx.doi.org/10.14419/ijet.v7i2.27.12084
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 IFIP International Federation for Information Processing
About this paper
Cite this paper
Misargopoulos, A. et al. (2022). Building a Knowledge-Intensive, Intent-Lean, Question Answering Chatbot in the Telecom Industry - Challenges and Solutions. In: Maglogiannis, I., Iliadis, L., Macintyre, J., Cortez, P. (eds) Artificial Intelligence Applications and Innovations. AIAI 2022 IFIP WG 12.5 International Workshops. AIAI 2022. IFIP Advances in Information and Communication Technology, vol 652. Springer, Cham. https://doi.org/10.1007/978-3-031-08341-9_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-08341-9_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-08340-2
Online ISBN: 978-3-031-08341-9
eBook Packages: Computer ScienceComputer Science (R0)
