Grounding Dialogue Systems via Knowledge Graph Aware Decoding with Pre-trained Transformers

TL;DR

This paper introduces a novel method for integrating Knowledge Graphs into dialogue response generation using a BERT-based model trained in an end-to-end manner, improving knowledge groundedness in responses.

Contribution

It proposes a new architecture that incorporates KGs via Graph Laplacian into a BERT model for end-to-end training and inference in dialogue systems.

Findings

Achieves higher Entity F1 scores than state-of-the-art models.

Effective integration of k-hop subgraphs improves response knowledge groundedness.

Applicable to both goal and non-goal oriented dialogues.

Abstract

Generating knowledge grounded responses in both goal and non-goal oriented dialogue systems is an important research challenge. Knowledge Graphs (KG) can be viewed as an abstraction of the real world, which can potentially facilitate a dialogue system to produce knowledge grounded responses. However, integrating KGs into the dialogue generation process in an end-to-end manner is a non-trivial task. This paper proposes a novel architecture for integrating KGs into the response generation process by training a BERT model that learns to answer using the elements of the KG (entities and relations) in a multi-task, end-to-end setting. The k-hop subgraph of the KG is incorporated into the model during training and inference using Graph Laplacian. Empirical evaluation suggests that the model achieves better knowledge groundedness (measured via Entity F1 score) compared to other state-of-the-art models for both goal and non-goal oriented dialogues.