When I used Base_EntityExtraction to process my PDF files that containing tables, the tool is treating the table columns as paragraphs. What I need is for the table cells in the same row to relate to each other. It is impossible to relate these data elements from the table cells because the tool processes one column at time as a paragraph. Is there a way to config the behaviour so that it processes one row at a time when it is extract data from tables?
Further to the question above, all the data elements extracted are having a PARENT_ID of -1, which means none of my data elements are related to each other. Is this something that have to configured for it to work?
You must be a registered user to add a comment. If you've already registered, sign in. Otherwise, register and sign in.