Screening through a broad pool: Towards better diversity for lexically constrained text generation

Changsen Yuan, Heyan Huang, Yixin Cao, Qianwen Cao

Abstract: Highlights•We highlight the multi-insertion to improve the diversity of text for lexically constrained text generation.•Masked text can increase text quality without using any extra knowledge.•Compared with baseline models on two publicly available datasets, the results show a superior performance of our model.