Abstract
Dialogue has long been used in human society to explain seemingly opaque concepts. In this paper we focus on how to better explain training models for neural networks, to entertain as well as inform. We present a multi-agent argumentation-based dialogue system to generate human understandable dialogue to explain backpropagation. The system incorporates a model of agent personality and introduces social elements between agents to produce characterful discussion. Natural language templates are used to render utterances in English.
Original language | English |
---|---|
Title of host publication | Artificial Intelligence and Cognitive Science 2021 |
Subtitle of host publication | The 29th Irish Conference on Artificial Intelligence and Cognitive Science 2021 Dublin, Republic of Ireland, December 9-10, 2021 |
Editors | Arjun Pakrashi, Ellen Rushe, Mehran Hossein Zadeh Bazargani, Brian Mac Namee |
Pages | 260-271 |
Number of pages | 12 |
Publication status | Published - 11 Mar 2022 |
Event | 29th Irish Conference on Artificial Intelligence and Cognitive Science - University College Dublin, Dublin, Ireland Duration: 9 Dec 2019 → 10 Dec 2021 Conference number: 29 https://aics2021.ucd.ie |
Publication series
Name | CEUR Workshop Proceedings |
---|---|
ISSN (Electronic) | 1613-0073 |
Conference
Conference | 29th Irish Conference on Artificial Intelligence and Cognitive Science |
---|---|
Abbreviated title | AICS21 |
Country/Territory | Ireland |
City | Dublin |
Period | 9/12/19 → 10/12/21 |
Internet address |
Keywords
- Backpropogation
- Explanation
- Argumentation
- Dialogue
- NLG