Collecting and Characterizing Natural Language Utterances for Specifying Data Visualizations

要旨

Natural language interfaces (NLIs) for data visualization are becoming increasingly popular both in academic research and in commercial software. Yet, there is a lack of empirical understanding of how people specify visualizations through natural language. We conducted an online study (N = 102), showing participants a series of visualizations and asking them to provide utterances they would pose to generate the displayed charts. From the responses, we curated a dataset of 893 utterances and characterized the utterances according to (1) their phrasing (e.g., commands, queries, questions) and (2) the information they contained (e.g., chart types, data aggregations). To help guide future research and development, we contribute this utterance dataset and discuss its applications toward the creation and benchmarking of NLIs for visualization.

著者
Arjun Srinivasan
Tableau Research, Seattle, Washington, United States
Nikhila Nyapathy
Georgia Institute of Technology, Atlanta, Georgia, United States
Bongshin Lee
Microsoft Research, Redmond, Washington, United States
Steven M.. Drucker
Microsoft Research, Redmond, Washington, United States
John Stasko
Georgia Institute of Technology, Atlanta, Georgia, United States
DOI

10.1145/3411764.3445400

論文URL

https://doi.org/10.1145/3411764.3445400

動画

会議: CHI 2021

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2021.acm.org/)

セッション: Novel Visualization Techniques

[A] Paper Room 09, 2021-05-11 17:00:00~2021-05-11 19:00:00 / [B] Paper Room 09, 2021-05-12 01:00:00~2021-05-12 03:00:00 / [C] Paper Room 09, 2021-05-12 09:00:00~2021-05-12 11:00:00
Paper Room 09
15 件の発表
2021-05-11 17:00:00
2021-05-11 19:00:00
日本語まとめ
読み込み中…