Papers by Angie Boggust
VisText: A Benchmark for Semantically Rich Chart Captioning (2023.acl-long)
Copied to clipboard
| Challenge: | Current approaches for automatically generating chart captions struggle to articulate the perceptual or cognitive features that are the hallmark of charts (e.g., complex trends and patterns). |
| Approach: | They propose a dataset of 12,441 pairs of charts and captions that describe charts’ construction, report key statistics, and identify perceptual and cognitive phenomena. |
| Outcome: | The proposed model generates coherent, semantically rich captions and performs on par with state-of-the-art chart captioning models across machine translation and text generation metrics. |