Tilbot: A Visual Design Platform to Facilitate Open Science Research into Conversational User Interfaces

Wit, Jan de; Braggaar, Anouck

doi:10.1145/3571884.3604403

Cited by 4 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As the software's authors, we have currently paired the system with a self-maintained version of the open-source Rocket.Chat 3 platform to make our chatbots publicly accessible 4 . Furthermore, as part of our future work, we plan to integrate the Tilbot software [5] as a visual platform to design the pre-scripted dialogue flows which then can be used in the HyLECA system.…”

Section: Relevance and Adaptabilitymentioning

confidence: 99%

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

Basar

Balaji

et al. 2023

Proceedings of the 5th International Conference on Conversational User Interfaces

View full text Add to dashboard Cite

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. CCS CONCEPTS• Human-centered computing → Natural language interfaces.

show abstract

Section: Relevance and Adaptabilitymentioning

confidence: 99%

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

Basar

Balaji

et al. 2023

Proceedings of the 5th International Conference on Conversational User Interfaces

View full text Add to dashboard Cite

show abstract

Leveraging Large Language Models as Simulated Users for Initial, Low-Cost Evaluations of Designed Conversations

de Wit

2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

EduCUI: The First International Workshop for Conversational User Interfaces in Education

Edwards,

de Araujo,

Desai

et al. 2024

ACM Conversational User Interfaces 2024

View full text Add to dashboard Cite

Tilbot: A Visual Design Platform to Facilitate Open Science Research into Conversational User Interfaces

Abstract: Figure 1: The design interface of Tilbot, where conversation designers can drag and drop different blocks to determine the flow of the conversation. On the right-hand side there is a simulator that can be used to test the interaction before deployment.

Cited by 4 publications

References 15 publications

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

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

Leveraging Large Language Models as Simulated Users for Initial, Low-Cost Evaluations of Designed Conversations

EduCUI: The First International Workshop for Conversational User Interfaces in Education

Contact Info

Product

Resources

About