SAPPHIRE: Approaches for Enhanced Concept-to-Text Generation
This work addresses concept-to-text generation for natural language processing applications, but it is incremental as it builds on existing models like BART and T5 with specific enhancements.
The paper tackles concept-to-text generation by proposing SAPPHIRE, a suite of improvements including set augmentation and phrase infilling, and demonstrates its effectiveness on the CommonGen task, showing noticeable performance gains through automatic and human evaluations.
We motivate and propose a suite of simple but effective improvements for concept-to-text generation called SAPPHIRE: Set Augmentation and Post-hoc PHrase Infilling and REcombination. We demonstrate their effectiveness on generative commonsense reasoning, a.k.a. the CommonGen task, through experiments using both BART and T5 models. Through extensive automatic and human evaluation, we show that SAPPHIRE noticeably improves model performance. An in-depth qualitative analysis illustrates that SAPPHIRE effectively addresses many issues of the baseline model generations, including lack of commonsense, insufficient specificity, and poor fluency.