Natural language generation, a part of artificial intelligence, studies the development of systems that produce text for different applications, for example the textual description of massive datasets or the automation of routine text creation.
The web is constantly growing and its contents, getting progressively more dynamic, are well-suited to automation by a realizer. However, existing realizers are not designed with the web in mind and their operation requires much knowledge, complicating their use.
JSrealB is a text realizer designed specifically for the web and easy to learn and use. This realizer allows its user to build a variety of French and English expressions and sentences, to add HTML tags to them and to easily integrate them into web pages.
Most of the documentation is in French and can be accessed here.
However, there are a number of resources written in English available on our website, including live demos.
- Random English text generation [JavaScript code]
- Random French text generation [JavaScript code]
- Conjugation and declension [JavaScript code]
- 99 bottles of beer: a repetitive text in English
- 1 km à pied: a repetitive text in French
- Date generation
- Exercises in style à la Raymond Queneau [JavaScript code] [The Exercices on Wikipedia]
An IDE is available to test and develop with JSrealB.
JSrealB was developed in 2015 by Paul Molins as part of an internship from INSA Lyon spent at RALI, University of Montreal. He built on the JSreal realizer created by Nicolas Daoust.
For more information, contact Guy Lapalme.