Knowledge Graph for NLG in the context of conversational agents

TL;DR

This paper reviews various architectures for knowledge graph-to-text generation in conversational agents, emphasizing the use of seq2seq Transformer models and discussing future research directions including emotional and multilingual aspects.

Contribution

It provides a comprehensive review of KG-to-text generation architectures and advocates for seq2seq Transformer models tailored to conversational agent constraints.

Findings

Seq2seq Transformer models are suitable for KG-to-text tasks in conversational agents.

Different architectures have specific advantages and limitations.

Future work includes refining datasets and exploring emotional and multilingual capabilities.

Abstract

The use of knowledge graphs (KGs) enhances the accuracy and comprehensiveness of the responses provided by a conversational agent. While generating answers during conversations consists in generating text from these KGs, it is still regarded as a challenging task that has gained significant attention in recent years. In this document, we provide a review of different architectures used for knowledge graph-to-text generation including: Graph Neural Networks, the Graph Transformer, and linearization with seq2seq models. We discuss the advantages and limitations of each architecture and conclude that the choice of architecture will depend on the specific requirements of the task at hand. We also highlight the importance of considering constraints such as execution time and model validity, particularly in the context of conversational agents. Based on these constraints and the availability of labeled data for the domains of DAVI, we choose to use seq2seq Transformer-based models (PLMs) for the Knowledge Graph-to-Text Generation task. We aim to refine benchmark datasets of kg-to-text generation on PLMs and to explore the emotional and multilingual dimensions in our future work. Overall, this review provides insights into the different approaches for knowledge graph-to-text generation and outlines future directions for research in this area.