Papers by Sina Zarrie
VIST5: An Adaptive, Retrieval-Augmented Language Model for Visualization-oriented Dialog (2023.emnlp-demo)
Copied to clipboard
| Challenge: | a number of visualization-oriented dialog systems rely on tailored dialog agents to analyze domain-specific data and operate domain- specific visualization tools and libraries. |
| Approach: | They propose a visualization-oriented dialog system that focuses on easy adaptability to an application domain and easy transferability of language-controllable visualization library functions between applications. |
| Outcome: | The proposed system is based on a retrieval-augmented T5 language model that leverages few-shot learning capabilities to enable a rapid adaptation of the system. |