Overview
Reveal offers robust language handling capabilities across multiple features. This article outlines the supported language functionalities, including extraction, identification, translation, and transcription.
Language Support Features
The language handling solution of Reveal consists of six main features:
Extraction of Electronic Text
Extraction of OCR Text
Language Identification
Language Translation
Transcription
User Interface Translation
Extraction of Electronic Text
Extraction of electronic text to UTF-8 Unicode is an automated step during processing within the Reveal platform.
Extraction of OCR Text
Reveal Processing supports over 120+ different languages during the OCR process. The OCR process can handle multiple languages within a single document in one pass (e.g., Chinese, Japanese, and Korean). So if a scanned document has Chinese, Japanese, and Korean, Reveal OCR will extract all 3 languages on a single OCR pass. Extraction of OCR text to UTF-8 Unicode is an automated step during processing within the Reveal platform.
Note
Review OCR only supports English. However, you can OCR other languages in Processing. For a full list of supported languages, refer to Appendix I - Supported Languages for OCR. This limitation does not affect the translation of native files and native file extractions.
Language Identification
Reveal supports 150+ different languages for language identification. This process uses a neural network AI n-gram approach to identify the top 3 languages and their respective percentage within the entire extracted and/or OCR text in a file. Language identification is an automated step in processing.
Language Translation
Reveal supports 75+ different languages for translation. This process uses an AI-driven approach that translates text from one language to another. Translation requires manual input by an Admin after files are loaded to Review. Users can leverage the languages and their percentages from language identification to execute the translation. Translation helps prioritize files but does not replace the need for native language review by reviewers. It is an additional functionality that allows admins and/or review managers to search for potentially relevant material in their native language and then prioritize the file for a reviewer fluent in the file's original language.
Transcription
Reveal supports 30+ different languages for transcription (converting speech to text). This process uses an AI-driven approach that transcribes spoken content into text. Admin input is required to input language transcription after loading files into Review. Users can leverage the languages identification results to assist with transcription.
User Interface Translation
Reveal supports 100+ languages for translating the user interface. Users can select their preferred language in settings.
Supported Languages For Translation
Reveal supports the following languages for translation:
Afrikaans | Albanian | Amharic | Arabic |
Armenian | Azerbaijani | Bengali | Bosnian |
Bulgarian | Catalan | Chinese (Simplified) | Chinese (Traditional) |
Croatian | Czech | Danish | Dari |
Dutch | English | Estonian | Farsi (Persian) |
Filipino, Tagalog | Finnish | French | French (Canada) |
Georgian | German | Greek | Gujarati |
Haitian Creole | Hausa | Hebrew | Hindi |
Hungarian | Icelandic | Indonesian | Irish |
Italian | Japanese | Kannada | Kazakh |
Korean | Latvian | Lithuanian | Macedonian |
Malay | Malayalam | Maltese | Marathi |
Mongolian | Norwegian | Pashto | Polish |
Portuguese | Portuguese (Portugal) | Punjabi | Romanian |
Russian | Serbian | Sinhala | Slovak |
Slovenian | Somali | Spanish | Spanish (Mexico) |
Swahili | Swedish | Tamil | Telugu |
Thai | Turkish | Ukrainian | Urdu |
Uzbek | Vietnamese | Welsh |