# Post-edit Analysis of Collective Biography Generation

## TL;DR

This paper analyzes human post-editing in template-based biography generation to identify ways to improve efficiency, accuracy, and stylistic consistency in high-precision text generation tasks.

## Contribution

It introduces a case study with visualization and manual analysis of edits to prioritize improvements in biography generation workflows.

## Key findings

- Edit flow visualization reveals common editing patterns.
- Manual analysis helps identify high-impact areas for efficiency gains.
- Focus on stylistic consistency improves user satisfaction.

## Abstract

Text generation is increasingly common but often requires manual post-editing where high precision is critical to end users. However, manual editing is expensive so we want to ensure this effort is focused on high-value tasks. And we want to maintain stylistic consistency, a particular challenge in crowd settings. We present a case study, analysing human post-editing in the context of a template-based biography generation system. An edit flow visualisation combined with manual characterisation of edits helps identify and prioritise work for improving end-to-end efficiency and accuracy.