Spaces:

MMDocIR
/

README

Running

daviddongdong commited on 12 days ago

Commit

aec823f

verified ·

1 Parent(s): 219862b

Update README.md

Files changed (1) hide show

README.md CHANGED Viewed

@@ -41,7 +41,7 @@ This task allows for a more nuanced content retrieval, honing in on specific inf
 ## 3. Evaluation Set
 ### 3.1 Document Analysis
-**MMDocIR** evluation set includes 313 long documents averaging 65.1 pages, categorized into ten main domains: research reports, administration&industry, tutorials&workshops, academic papers, brochures, financial reports, guidebooks, government documents, laws, and news articles.
 Different domains feature distinct distributions of multi-modal information. For instance, research reports, tutorials, workshops, and brochures predominantly contain images, whereas financial and industry documents are table-rich. In contrast, government and legal documents primarily comprise text. Overall, the modality distribution is: Text (60.4%), Image (18.8%), Table (16.7%), and other modalities (4.1%).
 ### 3.2 Question and Annotation Analysis

 ## 3. Evaluation Set
 ### 3.1 Document Analysis
+**MMDocIR** evaluation set includes 313 long documents averaging 65.1 pages, categorized into ten main domains: research reports, administration&industry, tutorials&workshops, academic papers, brochures, financial reports, guidebooks, government documents, laws, and news articles.
 Different domains feature distinct distributions of multi-modal information. For instance, research reports, tutorials, workshops, and brochures predominantly contain images, whereas financial and industry documents are table-rich. In contrast, government and legal documents primarily comprise text. Overall, the modality distribution is: Text (60.4%), Image (18.8%), Table (16.7%), and other modalities (4.1%).
 ### 3.2 Question and Annotation Analysis