# General Concepts of the NLG and the Platform (Intro)

//*Präambel, What's the platform for? How is it technically structured? What are its components? What are the basic functions?

The AX Semantics NLG Cloud is a software platform, that enables you to generate text from data. This can be used for any kind of text, e.g. product descriptions, business reports, journalistic application or chat bots.


Natural Language Generation, a subfield of artificial intelligence (AI), is a software process that automatically transforms data into written or spoken narrative. NLG is related to computational linguistics, natural language processing (NLP) and natural language understanding (NLU), the areas of AI concerned with human-to-machine and machine-to-human interaction.

# Accessing the Software

The web interface is a self-service portal integrated in the NLG Cloud. From here you have access to functionality such as data transfer, text generation and integration of automated content generation into your website.

cockpit.ax-semantics.com (opens new window)

# Components of the NLG Platform

  1. Webinterface NLG CLOUD with user management and data connection
  2. Composer configuration of the text project, data extraction), realtime view
  3. Massentextausgabe an der NLG CLOUD
  4. Direct API

# Processing Steps of NLG Projects

# Structured Data as requirement

Data input Text generation is based on structured data. Structured data means that data should be provided in separate data fields, e.g. you cannot use continuous text as data source. For further processing the data is analyzed and prepared. These analyses provide you with an evaluation of the data, such as the distribution of the values.

See also Analyze (opens new window)

# Deducing Conclusions and Reasoning

Take a look at the data and check which information you can extract from it.Data gets mapped against meanings and conclusions. Relevant information in the data is extracted and put into formal rulesets.

Your data gets mapped against meanings and conclusions. Relevant information in the data is extracted and put into formal rulesets. Your data gets mapped against meanings and conclusions. Relevant information in the data is extracted and put into formal rulesets. Constructing logical statements and connecting them into a text structure Grammar rendering (morphology, syntax)

# Story Planing and Text Conception

Text conception You decide which information the text should have, how this information should be formulated and how your text should be structured.

# Grammar, Morphology and Syntax Realization

Rule set In the rule set you can access your data and create logical evaluations about it. You can also define which words should be used for the outcomes of those evaluations.

# Languages

Currently, we support the following languages and regional variants in our self-service interface:

  • ar-SA: Arabic (Saudi-Arabia)
  • bg-BG: Bulgarian (Bulgaria)
  • cs-CZ: Czech (Czech Republic)
  • da-DK: Danish (Denmark)
  • de-AT: German (Austria)
  • de-CH: German (Switzerland)
  • de-DE: German (Germany)
  • en-GB English (Great Britain)
  • en-US: English (US)
  • el-GR: Greek (Greece)
  • es-ES: Spanish (Spain)
  • es-CL: Spanish (Chile)
  • fi-FI: Finnish (Finland)
  • fr-FR: French (France
  • fr-CH: French (Switzerland)
  • hr-HR: Croatian (Croatia)
  • hu-HU: Hungarian (Hungary)
  • uk-UA: Ukrainian (Ukraine)
  • it-IT: Italian (Italy)
  • ja-JP: Japanese (Japan)
  • lv-LV: Latvian (Latvia)
  • nl-NL: Dutch (Netherlands)
  • nb-NO: Norwegian Bokmål (Norway)
  • pl-PL: Polish (Poland)
  • pt-PT: Portuguese (Portugal)
  • pt-BR: Portuguese (Brasil)
  • ro-Ro: Romanian (Romania)
  • ru-RU: Russian (Russia
  • sk-SK: Slovak (Slovakia)
  • sl-SI: Slovenian (Slovenia)
  • sv-SE: Swedish (Sweden)
  • tr-TR: Turkish (Turkey)
  • zh-CN: Chinese (Simplified)

Additionally, the following languages are supported as well, please contact our support team to get these unlocked in your account:

Adyghe, Albanian, Arabic, Armenian, Asturian, Azeri, Bashkir, Basque, Belarusian, Bengali, Breton, Bulgarian, Catalan, Crimean-Tatar, Czech, Danish, Estonian, Faroese, Finnish, Friulian, Galician, Georgian, Greek, Haida, Hebrew, Hindi, Hungarian, Icelandic, Irish, Italian, Kabardian, Khaling, Kurmanji, Ladin, Latin, Latvian, Lithuanian, Livonian, Lower-Sorbian, Macedonian, Maltese, Navajo, Neapolitan, Northern-Sami, Norwegian-Bokmaal, Norwegian-Nynorsk, Occitan, Pashto, Persian, Portuguese, Quechua, Romanian, Sanskrit, Serbo-Croatian, Slovak, Slovene, Sorani, Spanish, Swahili, Swedish, Tatar, Turkish, Ukrainian, Urdu, Uzbek, Venetian, Votic, Welsh, Yiddish, Zulu, Dutch, English, French, German, Kannada, Polish, Russian, Cornish, Greenlandic, Karelian, Kashubian, Kazakh, Khakas, Mapudungun, Murrinhpatha, Norman, Scottish-Gaelic, Telugu, Tibetan, Turkmen