jsRealB: a bilingual text realiser for web programming
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 redaction.
The web is constantly growing and its contents, getting progressively more dynamic, are well-suited to automation by a realiser. However, existing realisers are not designed with the web in mind and their operation requires much knowledge, complicating their use.
jsRealB has been developped over the years under the direction of Guy Lapalme.
- Nicolas Daoust created the original concept (jsReal in French only) in Masters thesis (in French) in 2013.
- Paul Molins overhauled the system's architecture while keeping the original syntaxe to develop (jsRealB French-English) in his intership for the INSA of Lyon that he made at RALI in 2015;
- Francis Gauthier improved jsRealB during a summer NSERC internship at RALI in 2016;
- Guy Lapalme developped new demonstrations, improved the documentation and some parts of the systems and adapted it for node.js in 2018.
Sources for the programs, linguistic resources and demonstations are available on the RALI GitHub.
- Tutorial (in English)
- User Documentation (in English and French)
- Development Environment
- Demonstrations (in French and English)
- Observable notebook
For more information :
- The jsRealB Text Realizer: Organization and Use-cases, G. Lapalme (2021).
- JSreal: a text realizer for Web Programming, N. Daoust and G. Lapalme
- Demo paper presented at the ENLG 2015 conference
- A short paper summarizing the system's features
- Paul Molins' internship report [in French]
- Presentation of this work at RALI-OLST's seminar on 8 July 2015 [in French]
Contact Guy Lapalme.