Tech: Text Generation.
Sophisticated Natural
Language Generation:
generate written text

from data.

Everyday content production has a lot of use cases, where the underlying information is based on data: Product descriptions are written based on product fact sheets, business reports on some kind of BI data or from a spreadsheet, news are written from information like weather data.

Natural Language Generation turns this data into written content directly, without the need for a human writer.

Three components to write a text via software

Your data is the basis for the content itself;

An AI training contributes the information about the desired output, meaning of the data items, phrasing, styling, keywords, translation hints, etc.

The NLG Core Software (our "text-engine") interprets that data together with the AI training and adds grammatical, semantic and lexical information to produce the final output: a human-sounding narrative and styled text.

NLG Core Features

Any kind of text, any kind of style.

  • Text Quality: perfect human sounding text output, including html markup and dynamic keyword density;
  • Public Availability: easy setup, no programming, data exchange and training via web app;
  • Essential Writing: real-time content in 24 languages, millions of articles a day.

The Process of “data to text”

Step 1: Data Intake

Connect your system via API or use the webinterface

  • Data processing is totally automated via our REST API
  • Your system delivers the data into the NLG Cloud, each dataset represents one text 
  • The data is being cleansed and analysed and made ready for text processing

Step 2: Editorial Configuration

Define, what is important to your reader, and how it should be written. Define document structure, wordings, etc.

A ruleset is the customization part, that connects data to editorial notions. This allows to write about any topic, in your desired wording. Basically your definition of the output.

  • detecting, what is worthy to write about for each data item
  • selection and prioritization of linguistic direction
  • translation of individual words (like brand or product names)
  • text structure, markup/styles, keywords

Step 3: Grammatical Rendering

Grammatical features of the NLG Core

The NLG Core interprets that ruleset and connects it to grammar, using all grammatical phenomenas of each language.

  • Flexion of nouns and verbs
  • Adding articles and determiners
  • Setting plurals/singulars
  • Sentence structure, synonyms
  • Text length, using keywords …

Step 4: Output Processing

Receive your content.

The text output is then processed to match the output parameters and sent back to you.

  • Rendering markup and HTML styles
  • sent via webhook for real time production
  • provided via API for analysis

Grammatical Features


Automated content needs to be highly dynamic to render your content based on the data: Since you cannot anticipate every single data item, key or value, a grammatical engine is needed to take care of the correct grammar. 


Some Examples for grammatical features in the NLG Cloud

Setting the Case

Example Input from data: “dog” 

English Output

nominative: “The dog”
dative:  “I give the ball to the dog.”
accusative: “I see the dog.”
genitive:  “The dog’s toy”

German Output

nominative: “Der Hund”
dative:  “Ich gebe dem Hund den Ball.”
accusative: “Ich sehe den Hund.”
genitive:  “Das Spielzeug des Hundes”

Setting the Article

Example Input from data: “smartphone”

English Output

definite: “the smartphone”
indefinite:  “a smartphone”
demonstrative: “this smartphone”

German Output

definite: “das Smartphone”
indefinite:  “ein Smartphone”
demonstrative: “dieses Smartphone”

Setting the Pronoun

Example Input from data: “smartphone”

English Output

personal: “it”
demonstrative:  “this smartphone”
demonstrative2: “which smartphone”
which:  “which”

German Output

personal: “es”
demonstrative:  “dieses"
demonstrative2: “das”
which:  “welches”

Setting the Plural

Example Input from data: count of HDMI port

English Output

singular: “one HDMI port”
plural:  “two HDMI ports”

German Output

singular: “ein HDMI Anschluss”
plural:  “zwei HDMI Anschlüsse”

Much more Grammar

Some more include:

  • Setting the preposition
  • Converting numerals
  • In-sentence references between parts of speech
  • Conjunctions: correctly combining words into lists
  • Changing tense (present / past ; e.g. it is /it was)

The automation rules are configured by a human editor.

  • By giving your editorial input to the machine, your data will be interpreted to produce texts. Thousands of them, in seconds, with guaranteed quality;
  • Machine Learning assists you during the creation of the “smart text”;
  • You have full control over the linguistics and the content of the output.

Compose your text idea

  • Use the text-editor style UI for writing your base text;
  • Start with native-language content and then move on.

Start making your text “dynamic” with the Magic mode

  • Point + click GUI for making your text smart, link data, link extracted meaning;
  • Instant preview on element or sentence with your real data.

Extensive Preview and Q&A features

  • Single text preview;
  • Data interpretation debug;
  • “All Sentene Output” for viewing all extractable text element combinations: make your text ruleset releasable.

Add Variance to comply with SEO requirements

  • Use sentence variations for basic text variations for the same statement; Use synonyms for making dynamic word replacements;
  • Add fallback and dynamic elements for;
  • Use SEO-keyword features to let the engine select for the perfect keyword density and density deviation;
  • Use a defined company specific vocabulary.

Get Content Output - perfectly written like a human editor

  • Produce content at scale and in real-time, with 270 texts per second and 0.2s per text;
  • Update your text anytome without human intervention;
  • Do away with manual text exchange via files or edit forms.

Manage your text production and preview results

  • Use Bulk content production and text updates
  • Generate single document previews
  • Different options for guaranteed text delivery SLA available

Various options for Text delivery for any use case

  • Automation of content via push (as a webhook)
  • Pull content from the API
  • Manual text delivery via download

Try the only complete self-service
generation tool in the world.

Bring your writing to the future