Data-to-Text

A subfield of natural language generation (NLG) that automatically produces human-readable text from structured data, such as databases, spreadsheets, or sensor readings. Data-to-text systems analyze input data to identify patterns, trends, and salient features, then generate coherent natural language descriptions. In accessibility, data-to-text technology is important for making complex data visualizations — such as charts, graphs, maps, and dashboards — accessible to screen reader users by automatically generating textual descriptions that convey the meaning and patterns in the data, going beyond simple alt text to provide narrative summaries that capture trends, outliers, and relationships that sighted users would perceive visually.