PCFG-based Natural Language Interface Improves Generalization for Controlled Text Generation
This work addresses the limitation of categorical attribute interfaces in controlled text generation, offering a more flexible natural language-based solution for researchers and practitioners in NLP.
The paper tackles the problem of controlled text generation by introducing a natural language interface using a PCFG to embed control attributes into commands, finding that this approach effectively generalizes to unseen commands and attributes, with the enhanced conditional generation method serving as a strong baseline.
Existing work on controlled text generation (CTG) assumes a control interface of categorical attributes. In this work, we propose a natural language (NL) interface, where we craft a PCFG to embed the control attributes into natural language commands, and propose variants of existing CTG models that take commands as input. In our experiments, we design tailored setups to test model's generalization abilities. We find our PCFG-based command generation approach is effective for handling unseen commands compared to fix-set templates; our proposed NL models can effectively generalize to unseen attributes, a new ability enabled by the NL interface, as well as unseen attribute combinations. Interestingly, we discover that the simple conditional generation approach, enhanced with our proposed NL interface, is a strong baseline in those challenging settings.