Harvesting Creative Templates for Generating Stylistically Varied Restaurant Reviews
This addresses the problem of generating more engaging and varied language for dialogue systems in the restaurant domain, though it appears incremental as it builds on existing template-based methods.
The paper tackles the problem of limited stylistic variation in natural language generation by harvesting creative templates from restaurant reviews, resulting in learned templates that score highly on subjective measures of convincingness, interestingness, and naturalness compared to traditional templates.
Many of the creative and figurative elements that make language exciting are lost in translation in current natural language generation engines. In this paper, we explore a method to harvest templates from positive and negative reviews in the restaurant domain, with the goal of vastly expanding the types of stylistic variation available to the natural language generator. We learn hyperbolic adjective patterns that are representative of the strongly-valenced expressive language commonly used in either positive or negative reviews. We then identify and delexicalize entities, and use heuristics to extract generation templates from review sentences. We evaluate the learned templates against more traditional review templates, using subjective measures of "convincingness", "interestingness", and "naturalness". Our results show that the learned templates score highly on these measures. Finally, we analyze the linguistic categories that characterize the learned positive and negative templates. We plan to use the learned templates to improve the conversational style of dialogue systems in the restaurant domain.