Document AI

  • Tech Stack:Bert, LayoutLM, OCR, NER, BIOES Tagging, Information Extraction and Document Classification
  • Architecture Image 1
  • Project sample:
    Image 1 Image 2 Image 3 Image 4 Image 5 Image 6 Image 7 Image 8 Image 9

The project involved extracting valuable information from a vast collection of unstructured insurance documents. The average PDF length was 90 pages, and extracted information from many relevant sections pertaining to the insurance domain as per the client's requirements.