does it perform well on Name extraction?

[darsh169]

Has anyone trained this model for extracting person name from pdfs? how was the result and how much data is sufficient for better performance?

[SularuStefan]

I did, at first, I was trying to extract the whole name (first & last name), which proved to be quite unsuccessful (It returned a weird string like "a a ee a"). Then changed the "name" field into 2 different fields for first and last name and the results were pretty accurate. I was just trying to get the proof of concept, so I only used 25 PDF files as train data and ALL of them have the same layout pattern.