Abstract
Task-oriented conversational bots allow users to access services and perform tasks through natural language conversations. However, integrating these bots and software-enabled services has not kept pace with our ability to deploy individual devices and services. The main drawbacks of current bots and services integration techniques stem from the inherent development and maintenance cost. In addition, existing Natural Language Processing (NLP) techniques automate various tasks but the synthesis of API calls to support broad range of potentially complex user intents is still largely a manual and costly process. In this paper, we propose three types of reusable patterns for recognising compositional conversational flows and therefore automatically support increased complexity and expressivity during the conversation.
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.
Chatfuel: https://chatfuel.com/; FlowXO: https://flowxo.com/.
- 2.
DialogFlow: https://dialogflow.com/, Wit.ai: https://wit.ai/, Amazon Lex: https://aws.amazon.com/lex/, IBM Watson https://www.ibm.com/watson/.
- 3.
- 4.
Study materials and in-depth results available at https://tinyurl.com/25ad8jv6.
References
Allen, J., et al.: PLOW: a collaborative task learning agent. AAAI (2007)
Banchs, R.E., Jiang, R., Kim, S., Niswar, A., Yeo, K.H.: AIDA: artificial intelligent dialogue agent. In: Proceedings of the SIGDIAL 2013, pp. 145–147 (2013)
Bradley, N., Fritz, T., Holmes, R.: Context-aware conversational developer assistants. In: 40th International Conference on Software Engineering (ICSE) (2018)
Canonico, M., De. Russis, L.: A comparison and critique of natural language understanding tools. Cloud Comput. 2018, 120 (2018)
Chen, H., Liu, X., Yin, D., Tang, J.: A survey on dialogue systems: recent advances and new frontiers. ACM Sigkdd Explor. Newsl. 19(2), 25–35 (2017)
Chen, L., al.: Schema-guided multi-domain dialogue state tracking with graph attention neural networks. In: Proceedings of the AAAI 2020, vol. 34, pp. 7521–7528 (2020)
Fast, E., et al.: Iris: a conversational agent for complex tasks. In: CHI 2018 (2018)
Henderson, M.S.: Discriminative methods for statistical spoken dialogue systems. Ph.D. thesis, University of Cambridge (2015)
Hugging-Face: Fast coreference resolution in spacy with neural networks. https://spacy.io/universe/project/neuralcoref. Accessed 15 Nov 2020
Hutchby, I., Wooffitt, R.: Conversation analysis. Polity (2008)
Jain, M., Kota, R., Kumar, P., Patel, S.N.: Convey: exploring the use of a context view for chatbots. In: Proceedings of the CHI 2018, pp. 1–6 (2018)
John, R.J.L., Potti, N., Patel, J.M.: Ava: from data to insights through conversations. In: 8th Biennial Conference on Innovative Data Systems Research (2017)
López, A., Sànchez-Ferreres, J., Carmona, J., Padró, L.: From process models to chatbots. In: Giorgini, P., Weber, B. (eds.) CAiSE 2019. LNCS, vol. 11483, pp. 383–398. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-21290-2_24
Manning, C.D., Eric, M.: A copy-augmented sequence-to-sequence architecture gives good performance on task-oriented dialogue. In: EACL (2017)
Rastogi, A., et al.: Towards scalable multi-domain conversational agents: the schema-guided dialogue dataset. arXiv e-prints arXiv:1909.05855, September 2019
Reinhart, T.M.: The syntactic domain of anaphora. Ph.D. thesis, MIT (1976)
Su, P., et al.: Continuously learning neural dialogue management. CoRR (2016)
Ebert, J.: SOA with REST: principles, patterns & constraints for building enterprise solutions with REST by Thomas Erl, Benjamin Carlyle, Cesare Pautasso, Raj Balasubramanian. ACM SIGSOFT Softw. Eng. Notes 38(3), 32–33 (2013)
Wu, C.S., et al.: Transferable multi-domain state generator for task-oriented dialogue systems. arXiv preprint arXiv:1905.08743 (2019)
Xiaoxue, R., et al.: API-misuse detection driven by fine-grained API-constraint knowledge graph (2020)
Yannakakis, M.: Hierarchical state machines. In: van Leeuwen, J., Watanabe, O., Hagiya, M., Mosses, P.D., Ito, T. (eds.) TCS 2000. LNCS, vol. 1872, pp. 315–330. Springer, Heidelberg (2000). https://doi.org/10.1007/3-540-44929-9_24
Zamanirad, S.: Superimposition of natural language conversations over software enabled services. Ph.D. thesis, University of New South Wales, Australia (2019)
Zamanirad, S., et al.: Hierarchical state machine based conversation model and services. In: Proceedings of the CAiSE (2020)
Zamanirad, S., et al.: Programming bots by synthesizing natural language expressions into API invocations. In: Proceedings of the ASE 2017, pp. 832–837. IEEE (2017)
Zhang, Z., et al.: Memory-augmented dialogue management for task-oriented dialogue systems. ACM Trans. Inf. Syst. 37(3), 1–30 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Bouguelia, S., Brabra, H., Zamanirad, S., Benatallah, B., Baez, M., Kheddouci, H. (2021). Reusable Abstractions and Patterns for Recognising Compositional Conversational Flows. In: La Rosa, M., Sadiq, S., Teniente, E. (eds) Advanced Information Systems Engineering. CAiSE 2021. Lecture Notes in Computer Science(), vol 12751. Springer, Cham. https://doi.org/10.1007/978-3-030-79382-1_10
Download citation
DOI: https://doi.org/10.1007/978-3-030-79382-1_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-79381-4
Online ISBN: 978-3-030-79382-1
eBook Packages: Computer ScienceComputer Science (R0)