AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

DocEdit: Language-Guided Document Editing

Puneet Mathur, Rajiv Jain, Jiuxiang Gu, Franck Dernoncourt, Dinesh Manocha, Vlad I. Morariu

AAAI 2023 · Vision-language and multimodal › Human and embodied modeling · approach: Layout-aware document understanding · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use DocEditor instead of the strongest command-generation baselineDocEdit-PDF command generation · DocEdit-PDFEM (%): 31.6 -> 37.6Improved
Use DocEditor instead of the strongest command-generation baselineDocEdit-Design command generation · DocEdit-DesignEM (%): 32.8 -> 38.2Improved
Use DocEditor instead of TransVGDocEdit-PDF region-of-interest prediction · DocEdit-PDFTop-1 Acc (%): 25.34 -> 36.50Improved
Use DocEditor instead of TransVGDocEdit-Design region-of-interest prediction · DocEdit-DesignTop-1 Acc (%): 24.89 -> 34.34Improved
Add text embedding (ablation)DocEditor command generation · DocEdit-PDFEM (%): 6.7 -> 37.6Improved
Add text embedding (ablation)DocEditor command generation · DocEdit-DesignEM (%): 6.1 -> 38.2Improved
Add visual embedding (ablation)DocEditor command generation · DocEdit-PDFEM (%): 33.6 -> 37.6Improved
Add layout graph (ablation)DocEditor region-of-interest prediction · DocEdit-PDFTop-1 Acc (%): 14.48 -> 36.50Improved
Add bounding box regression loss (ablation)DocEditor command generation · DocEdit-PDFEM (%): 33.6 -> 37.6Improved
Add anchor box prediction loss (ablation)DocEditor command generation · DocEdit-DesignEM (%): 35.0 -> 38.2Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy