Experiments in Linear Template Combination using Genetic Algorithms
This work addresses the tactical component of Natural Language Generation for researchers, but it is incremental as it builds on existing template-based methods with a new optimization approach.
The authors tackled the problem of generating natural language by constructing sentences as sequences of locally grammatical templates, and they developed a baseline implementation using Genetic Algorithms to explore this search space, resulting in outputs of gapped text.
Natural Language Generation systems typically have two parts - strategic ('what to say') and tactical ('how to say'). We present our experiments in building an unsupervised corpus-driven template based tactical NLG system. We consider templates as a sequence of words containing gaps. Our idea is based on the observation that templates are grammatical locally (within their textual span). We posit the construction of a sentence as a highly restricted sequence of such templates. This work is an attempt to explore the resulting search space using Genetic Algorithms to arrive at acceptable solutions. We present a baseline implementation of this approach which outputs gapped text.