Hello I am new to DU.I am working on a project resume screening. So i wanted to understand in Document Understanding, do you classify Resume as structured or semi structured or unstructured document?
Structured document
Thank you for your quick reply. I just need to clarify Is not structured document supposed to have key-value pairs and tables. And since resumes comes in a wide ranges it often contains lot of text within paragraphs. Is it still structured? Can you help me understand this please.
- Structured Document:
- If a resume follows a consistent template or format where sections like contact information, education, work experience, skills, etc., are clearly delineated and can be reliably located using predefined rules or patterns, it can be considered structured. Structured documents are typically easier to extract information from programmatically without much variability in the location or format of data.
- Semi-Structured Document:
- Resumes that have some level of structure but may vary in the ordering of sections, use different headings, or have some optional sections can be classified as semi-structured. In semi-structured documents, there may be variations in how information is presented, requiring more flexible extraction techniques that account for these variations.
- Unstructured Document:
- If a resume lacks a consistent layout or template, with information scattered throughout the document without clear section headings or patterns, it is considered unstructured. Unstructured documents pose the greatest challenge for automated extraction because information may appear in different places and formats, requiring advanced natural language processing (NLP) techniques to interpret and extract relevant data.
1 Like
Thank you so much for such a detailed reply 
I hope your doubt clarified,So please mark it as solution so the loop closes
1 Like
Thank you for sharing
1 Like
This topic was automatically closed 3 days after the last reply. New replies are no longer allowed.