We describe a corpus-based approach to natural language generation (NLG). The approach has been implemented as a component of a spoken dialog system and a series of evaluations we...
Most previous work on trainable language generation has focused on two paradigms: (a) using a statistical model to rank a set of generated utterances, or (b) using statistics to i...
Generating test data for formal state based specifications is computationally expensive. This paper improves a framework that addresses this issue by representing the test data ge...
Karnig Derderian, Mercedes G. Merayo, Robert M. Hi...
This paper describes a top-down word image generation model for holistic handwritten word recognition. To generate a word image, it uses likelihoods based, respectively, on a ling...
This paper presents a novel Automatic Question Generation (AQG) approach that generates trigger questions as a form of support for students’ learning through writing. The approac...