Answering Questions about Charts and Generating Visual Explanations

要旨

People often use charts to analyze data, answer questions and explain their answers to others. In a formative study, we find that such human-generated questions and explanations commonly refer to visual features of charts. Based on this study, we developed an automatic chart question answering pipeline that generates visual explanations describing how the answer was obtained. Our pipeline first extracts the data and visual encodings from an input Vega-Lite chart. Then, given a natural language question about the chart, it transforms references to visual attributes into references to the data. It next applies a state-of-the-art machine learning algorithm to answer the transformed question. Finally, it uses a template-based approach to explain in natural language how the answer is determined from the chart's visual features. A user study finds that our pipeline-generated visual explanations significantly outperform in transparency and are comparable in usefulness and trust to human-generated explanations.

キーワード
Question answering
Visualization
Explainable AI
著者
Dae Hyun Kim
Stanford University, Stanford, CA, USA
Enamul Hoque
York University, Toronto, ON, Canada
Maneesh Agrawala
Stanford University, Stanford, CA, USA
DOI

10.1145/3313831.3376467

論文URL

https://doi.org/10.1145/3313831.3376467

動画

会議: CHI 2020

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2020.acm.org/)

セッション: Talk visually to me

Paper session
316A MAUI
5 件の発表
2020-04-28 20:00:00
2020-04-28 21:15:00
日本語まとめ
読み込み中…