Languages supported in Automation 360 IQ Bot
- 版本:
- 已更新: 2022/12/02
Languages supported in Automation 360 IQ Bot
Up to 31 languages are supported in IQ Bot. You can also access up to 190 languages in IQ Bot by using an OCR engine.
When you review the list of languages in IQ Bot, you will observe the
following:
- Some languages are listed multiple times as variants, for example, Norwegian, Norwegian (Bokmal), Norwegian (Nynorsk).
- Among languages that are written from right to left, only Arabic is currently supported on IQ Bot.
- For languages not in the IQ Bot UI by default:
- These rely on ABBYY FineReader Engine 12.2 for text segmentation and OCR, then IQ Bot for classification, extraction, and auto-correction.
- Contact your Cognitive Services or Sales Engineering representative to create IQ Bot custom domains to access these languages.
- In the SQL database and .json file, IQ Bot requires language codes for 160 of the additional languages to appear in the UI, and culture codes to allow numeric and date validation.
Note:
- For ABBYY FineReader Engine and Microsoft Azure Computer Vision OCR engine, IQ Bot uses its text segmentation + OCR.
- For Microsoft Azure Computer Vision OCR engine, user can select any language from IQ Bot's drop-down, but the API aims to auto-detect the language during processing, and override user selection.
The following table provides a list of supported languages in IQ Bot for various document types:
Language | Document types such as invoice, contracts, health insurance, purchase order, and so on | Document type - Other |
---|---|---|
English | X | X |
German | X | X |
French | X | X |
Spanish | X | X |
Italian | X | X |
Afrikaans | X | |
Arabic | X | |
Bulgarian | X | |
Catalan | X | |
Chinese (Simplified) | X | |
Chinese (Traditional) | X | |
Czech | X | |
Danish | X | |
Dutch | X | |
Flemish | X | |
Greek | X | |
Hungarian | X | |
Indonesian | X | |
Japanese | X | |
Korean | X | |
Latin | X | |
Malay | X | |
Norwegian | X | |
Polish | X | |
Portuguese | X | |
Romanian | X | |
Russian | X | |
Serbian (Latin) | X | |
Slovak | X | |
Swedish | X | |
Turkish | X |
The following table lists the languages that are supported in IQ Bot through a custom domain:
Abkhaz | Galician | Mari | Sioux (Dakota) |
Adyghe | Ganda | Maya | Slovenian |
Agul | German | Miao | Somali |
Albanian | German (new spelling) | Minangkabau | Sorbian |
Armenian (Eastern) | German (Luxembourg) | Russian and English | Sotho |
Armenian (Grabar) | Guarani | Mohawk | Sunda |
Armenian (Western) | Hani | Mongol | Swahili |
Avar | Hausa | Mordvin | Swazi |
Aymara | Hawaiian | Nahuatl | Tabassaran |
Bashkir | Icelandic | Nenets | Tagalog |
Basque | Ido | Nivkh | Tahitian |
Belarussian | Interlingua | Nogay | Tajik |
Bemba | Irish | NorwegianNynorsk and NorwegianBokmal | Tatar |
Blackfoot | Kabardian | Norwegian (Bokmal) | Thai |
Breton | Kalmyk | Norwegian (Nynorsk) | Jingpo |
Bugotu | Karachay-Balkar | Nyanja | Tongan |
Burmese | Karakalpak | Occidental | Tswana |
Buryat | Kasub | Ojibway | Tun |
Chamorro | Kawa | Old English | Turkmen |
Chechen | Kazakh | Old French | Turkmen (Latin) |
Chukcha | Khakas | Old German | Tuvan |
Chuvash | Khanty | Old Italian | Udmurt |
Corsican | Kikuyu | Old Slavonic | Uighur (Cyrillic) |
Crimean Tatar | Kirghiz | Old Spanish | Uighur (Latin) |
Croatian | Kongo | Ossetian | Ukrainian |
Crow | Korean (Hangul) | Papiamento | Uzbek (Cyrillic) |
Dargwa | Koryak | Tok Pisin | Uzbek (Latin) |
Dungan | Kpelle | Portuguese (Brazil) | Vietnamese |
Dutch (Netherlands) | Kumyk | Portuguese (Portugal) | Cebuano |
Eskimo (Cyrillic) | Lak | Provencal | Welsh |
Eskimo (Latin) | Sami (Lappish) | Quechua | Wolof |
Esperanto | Latvian | Rhaeto-Romanic | Xhosa |
Estonian | Latvian (language written in Gothic script) | Romanian (Moldavia) | Yakut |
Even | Lezgin | Romany | Yiddish |
Evenki | Lithuanian | Ruanda | Zapotec |
Faeroese | Luba | Rundi | Zulu |
Fijian | Macedonian | Russian (old spelling) | |
Finnish | Malagasy | Russian (with accents marking stress position) | |
Frisian | Malinke | Samoan | |
Friulian | Maltese | Selkup | |
Scottish Gaelic | Mansi | Serbian (Cyrillic) | |
Gagauz | Maori | Shona |
The following table provides you with links to supported languages for all IQ Bot supported OCR engines:
IQ Bot supported OCR engines | List of supported languages |
---|---|
ABBYY FineReader Engine | ABBYY FineReader Engine OCR supported languages |
Microsoft Azure Computer Vision OCR engine | https://docs.microsoft.com/en-us/azure/cognitive-services/computer-vision/language-support |
Google Vision API | https://cloud.google.com/vision/docs/languages |
Tesseract4 OCR 4.0.0 | https://tesseract-ocr.github.io/tessdoc/Data-Files-in-different-versions.html |
Tegaki API |
|
Note: The supported languages in IQ Bot must be
considered in concurrence with the OCR supported
languages.
Tip: If you are unable to see all languages in the IQ Bot UI or if IQ Bot is unable to extract data from
multiple languages in a document, troubleshoot the issue:
Unable to extract data from Multiple languages in a document (A-People login required)
Note: If you are adding custom
language to a custom domain, then you must retain the language ID across all
installations from where IQ Bot learning instances will be
exported and imported.