Tech: Generate text from your data with our Natural Language Generation platform.

Everyday content production has many use cases in which the underlying information is based on data: product descriptions are based on product fact sheets, business reports are built from some type of BI data or from a spreadsheet, and news is written from information such as weather data.

With the help of our Natural Language Generation software, you can turn this data into written content, time and cost efficiently.

The components to write content via software:

Your data itself is the basis for the content.

You decide how the data should appear in the text and how it should be interpreted. The AI learns from you which statements you want to make about a topic--depending on your data content--and how you want to formulate them.

The NLG Core software (our "text engine") interprets the data according to your specifications along with the AI training and adds grammatical and lexical information to produce the final result: human-sounding narrative and styled content.

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 110 languages, millions of articles a day

The Process of Data to Content

Step 1: Data Input

via API or web interface

  • Data processing is totally automated via our REST API.
  • Your system delivers the data into the NLG Cloud, with each dataset representing one content item.
  • The data is cleansed, analyzed, and prepared for text processing.

Step 2: Editorial Configuration

Structure, content, wording, language style and formulations

In your NLG project, text is created from your input and your data. You have the possibility to define content and logic for each topic and in each language. Here you create your definition of the output:

  • You define the output for the data values.
  • Speech style and wording are completely in your hands.
  • For multilingual projects, the text modules such as product type and features are translated once.
  • You create the text structure and adjust settings such as markup awards, text length, or keywords according to your wishes.

Step 3: Grammatical Rendering

grammatical features of the NLG Core

The NLG engine combines the set of rules with the grammar of the respective language and thus generates grammatically correct texts.

  • Flexion of adjectives, nouns, and verbs
  • Correct use of determiners and pronouns
  • Setting Numerus, Casus, and Genus

Step 4: Output Processing

The generated text for your data sets

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

  • Rendering markup and HTML styles
  • 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 grammar engine is required to ensure correct grammar. Some examples of 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

More examples 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, you ensure that your data will be interpreted to produce the desired content: thousands of text items, 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 content idea

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

Make your text “dynamic” with the Magic Mode

  • Point + click GUI for making your text smart, linking data and 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 Sentence Output” for viewing all extractable text element combinations: make your text ruleset releasable

Add variance to comply with SEO requirements

  • Sentence variations to vary text versions of the same statement
  • Synonyms to make dynamic word replacements
  • Fallback and dynamic elements for data faults
  • SEO keyword features to let the engine select the appropriate keyword density and density deviation 

Get real-time content output

  • Produce content at scale and in real time, with 270 content items per second and 0.2s per item.

  • Update your text anytime without human intervention.

  • Do away with manual content exchange via files or editing forms.

Manage your content production and preview results

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

A variety of options for content 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.