GenNext: A Consolidated Domain Adaptable NLG System
Frank Schilder, Blake Stephen Howald, Ravi Kondadadi · 2013
We introduce GenNext, an NLG system designed specifically to adapt quickly and easily to different domains. Given a domain corpus of historical texts, GenNext allows the user to generate a template bank organized by semantic concept via derived discourse representation structures in conjunction with general and domain-specific entity tags. Based on various features collected from the training corpus, the system statistically learns template representations and document structure and produces well–formed texts (as evaluated by crowdsourced and expert evaluations). In addition to domain adaptation, Gen-Next’s hybrid approach significantly reduces complexity as compared to traditional NLG systems by relying on templates (consolidating micro-planning and surface realization) and minimizing the need for domain experts. In this description, we provide details of GenNext’s theoretical perspective, architecture and evaluations of output. 1