LineCap: Line Charts for Data Visualization Captioning Models

TL;DR

LineCap introduces a new dataset of 3,528 figures for automated captioning of data visualizations, leveraging deep learning to improve accessibility and understanding of visual data.

Contribution

The paper presents the first dataset specifically for line chart captioning and demonstrates the application of deep learning models to automate figure captioning.

Findings

Successful application of deep learning models to caption line charts

Creation of a new dataset for figure captioning

Insights into dataset curation for visualization captioning

Abstract

Data visualization captions help readers understand the purpose of a visualization and are crucial for individuals with visual impairments. The prevalence of poor figure captions and the successful application of deep learning approaches to image captioning motivate the use of similar techniques for automated figure captioning. However, research in this field has been stunted by the lack of suitable datasets. We introduce LineCap, a novel figure captioning dataset of 3,528 figures, and we provide insights from curating this dataset and using end-to-end deep learning models for automated figure captioning.