What languages does IBM Watson support?

There is no correct answer to what languages IBM Watson currently supports. Each of the 28 services support different languages, services like AlchemyLanguage even supports different languages for each sub-api, sentiment (8) and language classification (97) as an example.

UPDATE: The supported language table below is now updated as of April 24th 2017. Differences from the prior table are documented in my Watson Pricing and Language Updates post, where I have documented the differences in language support as well as changes in Watson Pricing since my last post on Watson pricing from Aug 2016. Only the table is updated (and some typos corrected).

Unstructured data and languages is a tough nut to crack. To support all languages is not easy, but what is a bit frustrating with IBM Watson is that each service support different languages, naturally logical since it is different technologies and as an example it is easier to classify a blogpost as Swedish or Turkish compared to extract relationships or concepts as well as translate a text or sense emotions. Also, there is no Watson language support page that you can go to.

Challenges aside IBM Watson actually already support several languages for most services available today. This is impressive from several angles since many of the services actually require that Watson to be cognitive and learn the language from the beginning, just as we as humans do.

Watson language support per service

What I discovered is that it is really hard to find what language each service support, it is often buried deep in the documentation and only in a few cases listed on the main page for the service.

So, I decided to dig through the documentation and create a document that lists all services and what languages they support.

The list below is the result of me digging through the documentation of each and every Watson Service currently available.

APILanguage Support
LANGUAGE
Natural Language Understanding watson language.png
ConversationBrazilian Portuguese, English, French, Italian, Spanish, German, Traditional Chinese, Simplified Chinese, and Dutch. Arabic is supported through the use of the Conversation API but not through the tooling interface.
Document Serviceslanguage independent
Language Translationto / from (news domain) : english, arabic, brazilian, portuguese, french, spanish, german, italian. Spanish can also be translated to and from French.
to / from (conv domain) : english, arabic, brazilian, portuguese, french, spanish, italian
from english to (patent domain) – brazilian, portuguese, chinese, spanish
Natural Language Classifierenglish, arabic, brazilian portuguese, french, german, japanese, italian, and spanish.
Personality InsightRequest Languages: english, spanish, arabic, japanese
Response Languages: arabic, english, japanese, spanish, brazilian portuguese, french, german, italian, koreoa, simplified chinese, traditional chinese
Retrieve and Rankenglish, japanese, portuguese, spanish
Tone Analyzerenglish, french
SPEECH
Speech to Textus english, uk english, japanese, spanish, brazilian, portuguese, modern standard arabic, mandarin
Text to Speech (fragmented documentation)input: brazilian portuguese, english, french, german, italian, japanese, spanish
output: brazilian portuguese, us english, uk english, french, german, japanese, italian, castilian spanish, north american spanish
VISION
Visual RecognitionClassify image method: english, spanish, arabic and japanese.
Custom and all others: english
DATA INSIGHT
Discovery ServiceEnglish, Spanish, Portuguese-BR (updated 2017-09-27) and German (Discovery News only english language news).

I hope that IBM and the IBM Watson team soon will publish an official list that they maintain and update. The above list is accurate as of the date this post is published (UPDATE: This table is updated as of 24th of April 2017). I will try my best to update when new services becomes available or an existing one supports additional languages. If I find an official IBM Watson document that lists language support per service I will naturally update as well.

10 Comments

[…] IBM Watson language support. Unstructured data and languages is a tough nut to crack. To support all languages is not easy, but what is a bit frustrating with IBM Watson is that each service support different languages, naturally logic since it is different technologies and as an example it is easier to classify a blogpost as Swedish or Turkish compared to extract relashionships or concepts as well as translate a text or decide sentiment. […]

Hi Gareth,
Well, I would say you are both right and wrong. Yes, it is posted “somewhere” for each service/API, but it is not listed in a unified way for all services. it took me quite some time to actually put this list together, since the info mainly is available in the API documentation for each service/API.

A small disclaimer is that this post is more then 6 months old, so IBM might have created a page that describes all services and what language each support since the post was written, but a quick google did not indicate that so was the case If there is one, please post it, would love to have an official one.

Leave a Reply