{Heng Gong}

Abstract

This paper describes the primary system submitted by the author to the E2E NLG Challenge on the E2E Dataset (Novikova et al. (2017)). Based on the baseline system called TGen (Dusek and Jurcicek (2016)), the primary system uses REINFORCE to utilize multiple reference for single Meaning Representation during training, while the baseline model treated them as individual training instances.