DimonGen: Diversified Generative Commonsense Reasoning for Explaining Concept Relationships

TL;DR

DimonGen introduces a novel approach for generating diverse, contextually rich sentences describing concept relationships, supported by a new benchmark dataset and a two-stage retrieval and generation model called MoREE.

Contribution

The paper presents DimonGen and MoREE, a new framework for diversified commonsense reasoning in sentence generation, along with a benchmark dataset for this task.

Findings

MoREE outperforms baselines in quality and diversity

Generated sentences reflect various concept relationships

The approach enhances understanding of commonsense concepts

Abstract

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.