Difference between revisions of "Showstoppers for Ingredients Extraction and Analysis"

From Open Food Facts wiki
Jump to navigation Jump to search
Line 24: Line 24:
 
=== Step 4 - Fix errors with Bad OCRs ===
 
=== Step 4 - Fix errors with Bad OCRs ===
 
* Reprocess OCRs
 
* Reprocess OCRs
 +
** Done by Raphael Nov 2024
 +
* Overwrite old lists that are very bad
 
* Perform spellcheck
 
* Perform spellcheck
 
** [https://github.com/openfoodfacts/openfoodfacts-ai/issues/314 Use large language models (LLM) to perform ingredient list spellcheck]
 
** [https://github.com/openfoodfacts/openfoodfacts-ai/issues/314 Use large language models (LLM) to perform ingredient list spellcheck]
 +
 
=== Step 5 - Bad splitting into individual ingredients ===
 
=== Step 5 - Bad splitting into individual ingredients ===
 
* Add a multilingual no cut list of words like U.H.T Cat 1…
 
* Add a multilingual no cut list of words like U.H.T Cat 1…

Revision as of 15:54, 17 January 2025

Metrics

Step 1 - Remove pet food & Cosmetics

Step 2 - Fix ingredients stored in the wrong language

Step 3 - Fix errors of ingredients cutting

Step 4 - Fix errors with Bad OCRs

Step 5 - Bad splitting into individual ingredients

  • Add a multilingual no cut list of words like U.H.T Cat 1…

Step 6 - Bad ingredient properties recognition

Step 7 - Missing translations or synonyms

Step 8 - Truly untaxonomized ingredients

Step 9 - Missing or Bad CIQUAL associations

Step 10 - Bad or insufficient categorization

Step 11 - Bad nutrition

  • Clean nutrition

Step 12 - Additional data not the ingredient list

  • Origins, -25% de sel, …
  • Legal constraints added to taxonomies ?