Two-stage stochastic natural language generation for email synthesis by modeling sender style and topic structure

Abstract

This paper describes a two-stage process for stochastic generation of email, in which the first stage structures the emails according to sender style and topic structure (high-level generation), and the second stage synthesizes text content based on the particulars of an email element and the goals of a given communication (surface-level realization). Synthesized emails were rated in a preliminary experiment. The results indicate that sender style can be detected. In addition we found that stochastic generation performs better if applied at the word level than at an original-sentence level ("template-based") in terms of email coherence, sentence fluency, naturalness, and preference.