Teneo supports 86 languages covering various global language families, in addition to different dialects and variations for each language.

Teneo languages
Afrikaans Estonian Japanese Oromo Swahili (Kiswahili)
Albanian Ewe Kazakh Papiamento Swazi
Amharic Faroese Kinyarwanda Polish Swedish
Armenian Finnish Kirundi (Rundi) Portuguese (European/Brazilian) Tigrinya
Azerbaijani French Korean Quechuan (Quechua) Tsonga
Basque Frisian Kyrgyz Romanian Tswana (Setswana)
Belorussian Galician Latvian Romansh Turkish
Bengali/Bangla Georgian Lithuanian Russian Turkmen
Bosnian German Luxembourgish Sámi Ukrainian
Bulgarian Greek Macedonian Sango Uzbek
Catalan Gujarati Malagasy Scottish Gaelic Vietnamese
Chinese (Mandarin) Hindi Malay Serbian Welsh
Croatian Hungarian Maltese Shona Yoruba
Czech Icelandic Marathi Sinhala Zulu (isiZulu)
Danish Igbo Mongolian Slovak
Dutch Indonesian Nepali Slovene
English Irish Norwegian Somali
Esperanto Italian Odia Spanish

The Teneo Platform is a development environment for natural language solutions and a runtime Environment for delivering those natural language solutions to the end users. As such, it provides resources for understanding and working with natural languages easily. In this scenario, more is better: the more languages the platform can handle, the more desirable it becomes for the large clients that need to communicate with their customers in various languages; the more in depth understanding of and the richer the resources in each language, the faster the user can develop highly complex natural language solutions.

As mentioned above, today Teneo Platform users can develop natural language solutions in 86 languages. This means that the platform understands the alphabets/characters, identifies what a word and a sentence are (what’s more, in some languages specific machine learned Input Processors have been developed, such as part-of-speech taggers, named entity recognizers and an overall language detector). Natively Teneo also supports the creation of machine learned Intent Classification – defined on a project level to be bespoke for the solution – integrated directly within the editorial interface.

In addition to this the system is able to normalize and pre-process text (e.g. tolerate misspellings and abbreviations, perform morphological analysis) in all 86 languages. These features are called Natural Language Processing (NLP), or Input Processing within the Teneo Platform.

In addition to Input Processing, the Teneo Platform also offers higher level language resources, like lexicons and basic dialogue capabilities, in the sense of covering most commonly occurring scenarios; these are the Teneo Lexical Resources and Teneo Dialogue Resources, respectively. Please note that these features are also called Natural Language Understanding (NLU) and Natural Language Interaction (NLI), respectively.

Teneo Lexical Resources (TLRs) are Artificial Solutions' proprietary resources containing off-the-shelf building blocks (Language Objects) to be used for modelling NLI solutions in Teneo Studio. They come as components of the Teneo Platform and are structured and designed to facilitate understanding of a specific language. They have been pre-built and cover the common language conditions and phrases that Teneo applications will most likely need.

The Teneo Dialogue Resources (TDRs) are solutions with flow drafts which are used at the start of a project as a Template solution from which to create a solution. They are more than simply chit-chatting flows, they are the generic dialogue capabilities that an NLI application needs in order to be human-like, that is, to show social skills and personalized behavior, to simulate intelligence, to engage the user and to optimize the NLI application’s purpose.

Language Resources
Chinese (Mandarin) French Malay Swedish
Czech German Norwegian Turkish
Danish Indonesian Portuguese
Dutch Italian Russian
English Japanese Spanish

Was this page helpful?