DimonGen: Diversified Generative Commonsense Reasoning for Explaining Concept Relationships
This work addresses the need for comprehensive commonsense reasoning in AI, though it is incremental as it builds on existing datasets and methods.
The paper tackles the problem of generating diverse sentences to explain concept relationships in everyday scenarios, and shows that their proposed two-stage model MoREE outperforms strong baselines in both quality and diversity of generated sentences.
In this paper, we propose DimonGen, which aims to generate diverse sentences describing concept relationships in various everyday scenarios. To support this, we first create a benchmark dataset for this task by adapting the existing CommonGen dataset. We then propose a two-stage model called MoREE to generate the target sentences. MoREE consists of a mixture of retrievers model that retrieves diverse context sentences related to the given concepts, and a mixture of generators model that generates diverse sentences based on the retrieved contexts. We conduct experiments on the DimonGen task and show that MoREE outperforms strong baselines in terms of both the quality and diversity of the generated sentences. Our results demonstrate that MoREE is able to generate diverse sentences that reflect different relationships between concepts, leading to a comprehensive understanding of concept relationships.