HyLECA: A Framework for Developing Hybrid Long-term Engaging Controlled Conversational Agents

Erkan Basar; Divyaa Balaji; Linwei He; Iris Hendrickx; Emiel Krahmer; Gert Jan De Bruijn; Tibor Bosse

doi:10.1145/3571884.3604404

HyLECA: A Framework for Developing Hybrid Long-term Engaging Controlled Conversational Agents

Erkan Basar, Divyaa Balaji, Linwei He, Iris Hendrickx, Emiel Krahmer, Gert Jan De Bruijn, Tibor Bosse

Language, Communication and Cognition

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

5 Citations (Scopus)

Abstract

We present HyLECA, an open-source framework designed for the development of long-term engaging controlled conversational agents. HyLECA's dialogue manager employs a hybrid architecture, combining rule-based methods for controlled dialogue flows with retrieval-based and generation-based approaches to enhance the utterance variability and flexibility. The motivation behind HyLECA lies in enhancing user engagement and enjoyment in task-oriented chatbots by leveraging the natural language generation capabilities of open-domain large language models within the confines of predetermined dialogue flows. Moreover, we discuss the technical capabilities, potential applications, relevance, and adaptability of the system. Lastly, we report preliminary findings from integrating state-of-the-art large language models in simulating a conversation centred on smoking cessation.

Original language	English
Title of host publication	Proceedings of the 5th International Conference on Conversational User Interfaces, CUI 2023
Publisher	Association for Computing Machinery
Number of pages	5
ISBN (Electronic)	9798400700149
DOIs	https://doi.org/10.1145/3571884.3604404
Publication status	Published - 19 Jul 2023
Event	5th International Conference on Conversational User Interfaces, CUI 2023 - Eindhoven, Netherlands Duration: 19 Jul 2023 → 21 Jul 2023

Publication series

Name	Proceedings of the 5th International Conference on Conversational User Interfaces, CUI 2023

Conference

Conference	5th International Conference on Conversational User Interfaces, CUI 2023
Country/Territory	Netherlands
City	Eindhoven
Period	19/07/23 → 21/07/23

Keywords

hybrid conversational agents
natural language generation
task-oriented dialogue systems

Access to Document

10.1145/3571884.3604404

https://repository.ubn.ru.nl/bitstream/handle/2066/296306/1/296306.pdf

Cite this

Basar, E., Balaji, D., He, L., Hendrickx, I., Krahmer, E., De Bruijn, G. J., & Bosse, T. (2023). HyLECA: A Framework for Developing Hybrid Long-term Engaging Controlled Conversational Agents. In Proceedings of the 5th International Conference on Conversational User Interfaces, CUI 2023 Article 56 (Proceedings of the 5th International Conference on Conversational User Interfaces, CUI 2023). Association for Computing Machinery. https://doi.org/10.1145/3571884.3604404

Basar, Erkan ; Balaji, Divyaa ; He, Linwei et al. / HyLECA : A Framework for Developing Hybrid Long-term Engaging Controlled Conversational Agents. Proceedings of the 5th International Conference on Conversational User Interfaces, CUI 2023. Association for Computing Machinery, 2023. (Proceedings of the 5th International Conference on Conversational User Interfaces, CUI 2023).

@inproceedings{0b8c4ff2ac874bf3b6fbbd86bd5bc2a5,

title = "HyLECA: A Framework for Developing Hybrid Long-term Engaging Controlled Conversational Agents",

abstract = "We present HyLECA, an open-source framework designed for the development of long-term engaging controlled conversational agents. HyLECA's dialogue manager employs a hybrid architecture, combining rule-based methods for controlled dialogue flows with retrieval-based and generation-based approaches to enhance the utterance variability and flexibility. The motivation behind HyLECA lies in enhancing user engagement and enjoyment in task-oriented chatbots by leveraging the natural language generation capabilities of open-domain large language models within the confines of predetermined dialogue flows. Moreover, we discuss the technical capabilities, potential applications, relevance, and adaptability of the system. Lastly, we report preliminary findings from integrating state-of-the-art large language models in simulating a conversation centred on smoking cessation.",

keywords = "hybrid conversational agents, natural language generation, task-oriented dialogue systems",

author = "Erkan Basar and Divyaa Balaji and Linwei He and Iris Hendrickx and Emiel Krahmer and {De Bruijn}, {Gert Jan} and Tibor Bosse",

note = "Publisher Copyright: {\textcopyright} 2023 Owner/Author.; 5th International Conference on Conversational User Interfaces, CUI 2023 ; Conference date: 19-07-2023 Through 21-07-2023",

year = "2023",

month = jul,

day = "19",

doi = "10.1145/3571884.3604404",

language = "English",

series = "Proceedings of the 5th International Conference on Conversational User Interfaces, CUI 2023",

publisher = "Association for Computing Machinery",

booktitle = "Proceedings of the 5th International Conference on Conversational User Interfaces, CUI 2023",

address = "United States",

}

Basar, E, Balaji, D, He, L, Hendrickx, I, Krahmer, E, De Bruijn, GJ & Bosse, T 2023, HyLECA: A Framework for Developing Hybrid Long-term Engaging Controlled Conversational Agents. in Proceedings of the 5th International Conference on Conversational User Interfaces, CUI 2023., 56, Proceedings of the 5th International Conference on Conversational User Interfaces, CUI 2023, Association for Computing Machinery, 5th International Conference on Conversational User Interfaces, CUI 2023, Eindhoven, Netherlands, 19/07/23. https://doi.org/10.1145/3571884.3604404

HyLECA: A Framework for Developing Hybrid Long-term Engaging Controlled Conversational Agents. / Basar, Erkan; Balaji, Divyaa; He, Linwei et al.
Proceedings of the 5th International Conference on Conversational User Interfaces, CUI 2023. Association for Computing Machinery, 2023. 56 (Proceedings of the 5th International Conference on Conversational User Interfaces, CUI 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

TY - GEN

T1 - HyLECA

T2 - 5th International Conference on Conversational User Interfaces, CUI 2023

AU - Basar, Erkan

AU - Balaji, Divyaa

AU - He, Linwei

AU - Hendrickx, Iris

AU - Krahmer, Emiel

AU - De Bruijn, Gert Jan

AU - Bosse, Tibor

PY - 2023/7/19

Y1 - 2023/7/19

N2 - We present HyLECA, an open-source framework designed for the development of long-term engaging controlled conversational agents. HyLECA's dialogue manager employs a hybrid architecture, combining rule-based methods for controlled dialogue flows with retrieval-based and generation-based approaches to enhance the utterance variability and flexibility. The motivation behind HyLECA lies in enhancing user engagement and enjoyment in task-oriented chatbots by leveraging the natural language generation capabilities of open-domain large language models within the confines of predetermined dialogue flows. Moreover, we discuss the technical capabilities, potential applications, relevance, and adaptability of the system. Lastly, we report preliminary findings from integrating state-of-the-art large language models in simulating a conversation centred on smoking cessation.

AB - We present HyLECA, an open-source framework designed for the development of long-term engaging controlled conversational agents. HyLECA's dialogue manager employs a hybrid architecture, combining rule-based methods for controlled dialogue flows with retrieval-based and generation-based approaches to enhance the utterance variability and flexibility. The motivation behind HyLECA lies in enhancing user engagement and enjoyment in task-oriented chatbots by leveraging the natural language generation capabilities of open-domain large language models within the confines of predetermined dialogue flows. Moreover, we discuss the technical capabilities, potential applications, relevance, and adaptability of the system. Lastly, we report preliminary findings from integrating state-of-the-art large language models in simulating a conversation centred on smoking cessation.

KW - hybrid conversational agents

KW - natural language generation

KW - task-oriented dialogue systems

UR - http://www.scopus.com/inward/record.url?scp=85167831458&partnerID=8YFLogxK

U2 - 10.1145/3571884.3604404

DO - 10.1145/3571884.3604404

M3 - Conference contribution

AN - SCOPUS:85167831458

T3 - Proceedings of the 5th International Conference on Conversational User Interfaces, CUI 2023

BT - Proceedings of the 5th International Conference on Conversational User Interfaces, CUI 2023

PB - Association for Computing Machinery

Y2 - 19 July 2023 through 21 July 2023

ER -

Basar E, Balaji D, He L, Hendrickx I, Krahmer E, De Bruijn GJ et al. HyLECA: A Framework for Developing Hybrid Long-term Engaging Controlled Conversational Agents. In Proceedings of the 5th International Conference on Conversational User Interfaces, CUI 2023. Association for Computing Machinery. 2023. 56. (Proceedings of the 5th International Conference on Conversational User Interfaces, CUI 2023). doi: 10.1145/3571884.3604404

HyLECA: A Framework for Developing Hybrid Long-term Engaging Controlled Conversational Agents

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this