Retrieval Enhanced Model for Commonsense Generation
It addresses the challenge of generating plausible everyday scenarios for AI systems, but is incremental as it builds on existing retrieval and fine-tuning techniques.
The paper tackles commonsense generation by enhancing pre-trained language models with retrieval methods, achieving new state-of-the-art results on the CommonGen benchmark.
Commonsense generation is a challenging task of generating a plausible sentence describing an everyday scenario using provided concepts. Its requirement of reasoning over commonsense knowledge and compositional generalization ability even puzzles strong pre-trained language generation models. We propose a novel framework using retrieval methods to enhance both the pre-training and fine-tuning for commonsense generation. We retrieve prototype sentence candidates by concept matching and use them as auxiliary input. For fine-tuning, we further boost its performance with a trainable sentence retriever. We demonstrate experimentally on the large-scale CommonGen benchmark that our approach achieves new state-of-the-art results.