Hierarchical template transformer for fine-grained sentiment controllable generation

作者：

Highlights：

• The proposed hierarchical framework can better control the fine-grained sentiment.

• The POS sequence can effectively guide the Transformers to generate more fluent text.

• We built a fine-grained sentiment controllable generation (FSCG-80) corpus.

摘要

•The proposed hierarchical framework can better control the fine-grained sentiment.•The POS sequence can effectively guide the Transformers to generate more fluent text.•We built a fine-grained sentiment controllable generation (FSCG-80) corpus.

论文关键词：Fine-grained text generation,Sentiment controllable generation,Sequence-to-sequence learning,Transformers

论文评审过程：Received 4 April 2022, Revised 23 July 2022, Accepted 23 July 2022, Available online 8 August 2022, Version of Record 8 August 2022.

论文官网地址：https://doi.org/10.1016/j.ipm.2022.103048