GE-Blender: Graph-Based Knowledge Enhancement for Blender

TL;DR

This paper introduces GE-Blender, a graph-based method that enhances dialogue generation by incorporating entity context and handling unseen entities through a graph structure and auxiliary tasks, improving performance on Wikipedia dialogues.

Contribution

The paper proposes a novel graph-based approach with entity context enhancement and an entity tag prediction task for better handling of unseen entities in dialogue generation.

Findings

Outperforms state-of-the-art on Wizard of Wikipedia

Effective in modeling unseen entities

Improves dialogue coherence with entity context

Abstract

Although the great success of open-domain dialogue generation, unseen entities can have a large impact on the dialogue generation task. It leads to performance degradation of the model in the dialog generation. Previous researches used retrieved knowledge of seen entities as the auxiliary data to enhance the representation of the model. Nevertheless, logical explanation of unseen entities remains unexplored, such as possible co-occurrence or semantically similar words of them and their entity category. In this work, we propose an approach to address the challenge above. We construct a graph by extracting entity nodes in them, enhancing the representation of the context of the unseen entity with the entity's 1-hop surrounding nodes. Furthermore, We added the named entity tag prediction task to apply the problem that the unseen entity does not exist in the graph. We conduct our experiments on an open dataset Wizard of Wikipedia and the empirical results indicate that our approach outperforms the state-of-the-art approaches on Wizard of Wikipedia.