Towards Attribute-Entangled Controllable Text Generation: A Pilot Study of Blessing Generation
This work introduces a new research direction for controllable text generation, specifically for blessing generation, which is incremental as it builds on existing CTG methods by focusing on attribute entanglement.
The paper tackles the challenge of generating diverse blessing texts by addressing attribute entanglement in controllable text generation, resulting in the creation of the EBleT dataset with 293K annotated sentences and novel evaluation metrics for baseline models.
Controllable Text Generation (CTG) has obtained great success due to its fine-grained generation ability obtained by focusing on multiple attributes. However, most existing CTG researches overlook how to utilize the attribute entanglement to enhance the diversity of the controlled generated texts. Facing this dilemma, we focus on a novel CTG scenario, i.e., blessing generation which is challenging because high-quality blessing texts require CTG models to comprehensively consider the entanglement between multiple attributes (e.g., objects and occasions). To promote the research on blessing generation, we present EBleT, a large-scale Entangled Blessing Text dataset containing 293K English sentences annotated with multiple attributes. Furthermore, we propose novel evaluation metrics to measure the quality of the blessing texts generated by the baseline models we designed. Our study opens a new research direction for controllable text generation and enables the development of attribute-entangled CTG models. Our dataset and source codes are available at \url{https://github.com/huangshulin123/Blessing-Generation}.