Ontogen : a knowledge-based approach to natural language generation

Abstract

A long-standing objective of artificial intelligence research has been to build collaborative agents that can communicate with humans via natural language. The fields of artificial intelligence and human-computer interaction have stake in building such agents that can communicate in a way that not only feels natural to us, but also opens the door to new ways in which humans can interact with agents beyond simple task automation. OntoGen is a Natural Language Generation (NLG) system that produces text from semantic meaning representations and generates grammatically correct and contextually relevant language. It is a rendering service for the OntoAgent cognitive architecture and provides the framework with the ability to generate language in a dialog context