Modeling informational novelty in a conversational system with a hybrid statistical and grammar-based approach to natural language generation

Abstract

We present a hybrid statistical and grammar-based system for surface natural language generation (NLG) that uses grammar rules, conditions on using those grammar rules, and corpus statistics to determine the word order. We also describe how this surface NLG module is implemented in a prototype conversational system, and how it attempts to model informational novelty by varying the word order. Using a combination of rules and statistical information, the conversational system expresses the novel information differently than the given information, based on the run-time dialog state. We also discuss our plans for evaluating the generation strategy.