Intentable is a mixed-initiative caption authoring system that allows the author to steer an automatic caption generation process to reflect their intents on captions. In this work, We first derive grammar for specifying the intents, i.e., a caption recipe, and build a neural network that generates caption sentences given a recipe. Our quantitative evaluation revealed that our intent-based generation system not only allows the author to engage in the generation process but also produces more fluent captions than the previous end-to-end approaches without user intervention. Finally, we demonstrate the versatility of our system such as context adaptation, unit conversion, and sentence reordering.
Jiwon Choi and Jaemin Jo
Proceedings of 2022 IEEE Visualization and Visual Analytics (VIS), pp. 40-44, Oklahoma City, USA, 2022.
TBA
@inproceedings{choi2022intentable,
title={Intentable: A Mixed-Initiative System for Intent-Based Chart Captioning},
author={Choi, Jiwon and Jo, Jaemin},
booktitle={2022 IEEE Visualization and Visual Analytics (VIS)},
pages={40--44},
year={2022},
organization={IEEE}
}