- Release Notes
- April 2024
- March 2024
- February 2024
- January 2024
March 2024
Bug fixes
Fixed an issue where the scroll position is occasionally reset during annotation while documents are processing.
What's new
The recommendations interface from the Build section is improved. Recommendations are now split between classification and extraction so you can check them separately, depending on your needs.
Bug fixes
- Fixed an issue where the displayed document was not preserved after reloading the browser window during annotation.
- Fixed an issue where table data was missing from the table view on some documents, even though the values were visible in the Fields panel.
- Fixed an issue where the two-letter hotkeys were not working during annotation.
Bug fixes
When loading a document for the first time, the confirmation badge is occasionally displayed on the currently selected document, even though not all fields are confirmed. This is now fixed and the confirmation badge is no longer displayed when a document is loaded for the first time.
Bug fixes
Fixed an issue where the order of numbers in Hebrew is reversed in Validation Station.
Bug fixes
Fixed an issue where changing the OCR Method field in Project Settings disabled the Save button.
What's new
UiPath Extended Languages OCR in Public Preview
We are excited to announce that our latest OCR engine, UiPath Extended Languages OCR, is now in Public Preview. The new OCR is capable of digitizing documents in over 200 languages, bringing a significant improvement over its predecessor, especially in regards to Chinese, Japanese, and Korean. Additionally, it can process documents in Thai, Vietnamese, all major languages from India, as well as languages using the Cyrilic alphabet, and Greek.
The UiPath Extended Languages OCR is currently only available as a public endpoint.
Released in Data Extraction ML packages | v23.10.4
A new version for the out-of-the-box pre-trained ML packages is now available for general usage.
This release brings improved accuracy for datasets smaller than 400 pages.
What's new
- DocumentUnderstandingOCR Endpoints | v24.3.2
- Data Extraction ML Packages | v23.10.4
A new version for the Document Understanding OCR and out-of-the-box pre-trained ML packages is now available for general usage.
- The accuracy for Turkish (TUR) is improved. The performance for characters with diacritics (such as Ç, ç, Ğ, ğ, I, ı, İ, i, Ş, ş, Ö, ö, Ü, ü) is improved.
- The accuracy for Eastern-Arabic numerals (٠, ١, ٢, ٣, ٤, ٥, ٦, ٧, ٨, ٩) is improved.