Knowledge acquisition for dialogue agents using reinforcement learning on graph representations
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910505485991936 |
|---|---|
| author | Santamaria, Selene Baez Wang, Shihan Vossen, Piek |
| author_facet | Santamaria, Selene Baez Wang, Shihan Vossen, Piek |
| contents | We develop an artificial agent motivated to augment its knowledge base beyond its initial training. The agent actively participates in dialogues with other agents, strategically acquiring new information. The agent models its knowledge as an RDF knowledge graph, integrating new beliefs acquired through conversation. Responses in dialogue are generated by identifying graph patterns around these new integrated beliefs. We show that policies can be learned using reinforcement learning to select effective graph patterns during an interaction, without relying on explicit user feedback. Within this context, our study is a proof of concept for leveraging users as effective sources of information. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_19500 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Knowledge acquisition for dialogue agents using reinforcement learning on graph representations Santamaria, Selene Baez Wang, Shihan Vossen, Piek Artificial Intelligence Computation and Language We develop an artificial agent motivated to augment its knowledge base beyond its initial training. The agent actively participates in dialogues with other agents, strategically acquiring new information. The agent models its knowledge as an RDF knowledge graph, integrating new beliefs acquired through conversation. Responses in dialogue are generated by identifying graph patterns around these new integrated beliefs. We show that policies can be learned using reinforcement learning to select effective graph patterns during an interaction, without relying on explicit user feedback. Within this context, our study is a proof of concept for leveraging users as effective sources of information. |
| title | Knowledge acquisition for dialogue agents using reinforcement learning on graph representations |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2406.19500 |