Corporate Website

Multilingual Services

Client

  • Global provider of data and information services, which enables companies to improve compliance with Environmental, Health & Safety (EH&S) regulations and supply chain obligations through the entire lifecycle of chemicals and products

Client Requirements

  • A reliable partner to assist in indexing of Multilingual Safety Data Sheets (SDS),capturing multilingual content presented under SDS document headings
  • SDS source files originate from thousands of manufacturers worldwide in non-searchable image/PDF format
  • Documents contained text and tabular data along with picture images under their various headings
  • Client was facing a challenge in accurate machine capturing of the multilingual content in UTF-8 text format at an optimized cost due to fuzzy appearance of content, character fonts not available with client, besides others
  • Maintain the source document format for the captured content
  • Pictures to be captured separately along with formatted text file for each document and marked in a text file at exact place of their occurrence for usage in client's downstream process
  • Due to above, language experts were manually keying information, leading to higher costs and process time

Our Solution

  • Reviewed client requirements and presented a customized workflow
  • Workflow involved deployment of multiple specialized OCR engines backed with in-house format utilities, addressing all deliverable requirements at optimum cost
  • Feedback was incorporated into the process to further refine the deliverables
  • Maintained quality of captured content through statistical quality control tools