Talk Me Through It: Developing Effective Systems for Chart Authoring
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908779453349888 |
|---|---|
| author | Ponochevnyi, Nazar Kim, Young-Ho Williams, Joseph Jay Kuzminykh, Anastasia |
| author_facet | Ponochevnyi, Nazar Kim, Young-Ho Williams, Joseph Jay Kuzminykh, Anastasia |
| contents | Recent chart-authoring systems increasingly focus on natural-language input, enabling users to form a mental image of the chart they wish to create and express this intent using spoken instructions (spoken imagined-chart data). Yet these systems are predominantly trained on typed instructions written while viewing the target chart (typed existing-chart data). While the cognitive processes for describing an existing chart arguably differ from those for creating a new chart, the structural differences in the corresponding prompts remain underexplored. We present empirical findings on the structural differences among spoken imagined-chart instructions, typed imagined-chart instructions, and typed existing-chart instructions for chart creation, showing that imagined-chart prompts contain richer command formats, element specifications, and complex linguistic features, especially in spoken instructions. We then compare the performance of systems trained on spoken imagined-chart data versus typed existing-chart data, finding that the first system outperforms the second one on both voice and text input, highlighting the necessity of targeted training on spoken imagined-chart data. We conclude with design guidelines for chart-authoring systems to improve performance in real-world scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_14707 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Talk Me Through It: Developing Effective Systems for Chart Authoring Ponochevnyi, Nazar Kim, Young-Ho Williams, Joseph Jay Kuzminykh, Anastasia Human-Computer Interaction Recent chart-authoring systems increasingly focus on natural-language input, enabling users to form a mental image of the chart they wish to create and express this intent using spoken instructions (spoken imagined-chart data). Yet these systems are predominantly trained on typed instructions written while viewing the target chart (typed existing-chart data). While the cognitive processes for describing an existing chart arguably differ from those for creating a new chart, the structural differences in the corresponding prompts remain underexplored. We present empirical findings on the structural differences among spoken imagined-chart instructions, typed imagined-chart instructions, and typed existing-chart instructions for chart creation, showing that imagined-chart prompts contain richer command formats, element specifications, and complex linguistic features, especially in spoken instructions. We then compare the performance of systems trained on spoken imagined-chart data versus typed existing-chart data, finding that the first system outperforms the second one on both voice and text input, highlighting the necessity of targeted training on spoken imagined-chart data. We conclude with design guidelines for chart-authoring systems to improve performance in real-world scenarios. |
| title | Talk Me Through It: Developing Effective Systems for Chart Authoring |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2601.14707 |