Knowledge Center next icon Natural Language Processing (NLP)
Nov 14, 2022
1 minute read

Natural Language Processing (NLP)

Natural Language Processing (NLP) toggle

Natural Language Processing

To process and understand incoming end-user questions, Conversational AI Cloud uses a Natural Language Processing (NLP) pipeline consisting of several steps. This article explains the different parts that make up Conversational AI Cloud’s NLP.

image.png

Language Support

regionlanguagem of speakerssimple matchingbasic NLPfull NLPculture
Western Europe/WorldEnglish360en
Western EuropeDutch21nl
Western EuropeFrench75fr
Western EuropeGerman89de
Western EuropeItalian59it
Western Europe/Latin AmericaSpanish405es
Eastern EuropePolish40pl
Eastern EuropeUkrainian30uk
Eastern EuropeRomanian24ro
Eastern EuropeHungarian13hu
Eastern EuropeSlovak12sl
Eastern EuropeCzech10cs
Northern EuropeSwedish9sv
Northern EuropeDanish6da
Northern EuropeNorwegian5no
Northern EuropeFinnish5fi
Southern EuropeGreek12el
Southern Europe/Latin AmericaPortuguese215pt
Southern EuropeSerbo-Croatian19sr,hr
East AsiaSimplified Chinese1052zh-CN
East AsiaTraditional Chinese45zh-HK
Middle East/WorldArabic280ar
Middle EastTurkish63tr

Basic NLP includes stemming & lemmatization – this is needed for basic production.
Full NLP includes language-specific rules for cleanups, overrides, and rephrase.

Note: Languages that are not on this list, can currently only be used in FAQ projects, so without an open search for users. This is because in an FAQ project, no natural language processing is needed. The Questions are predefined, so recognition is strictly based on a keyword search.

group icon
Get support

Can’t find the answer you are looking for?
Ask for the help of our chatbot, or get in touch with our support team.

Contact Support
Is this region a better fit for you?
Go
close icon