Triples-to-Text Generation with Reinforcement Learning Based Graph-augmented Neural Networks

TL;DR

This paper introduces a novel graph-augmented neural network model with reinforcement learning to improve RDF-to-text generation, effectively capturing structural information and enhancing the faithfulness of generated descriptions.

Contribution

It proposes a new model combining graph-augmented encoders and reinforcement learning with information extraction rewards to better model structure and improve text faithfulness.

Findings

Outperforms state-of-the-art baselines on benchmark datasets.

Reinforcement learning reward improves generated text faithfulness.

Effectively models local and global structural information in RDF triples.

Abstract

Considering a collection of RDF triples, the RDF-to-text generation task aims to generate a text description. Most previous methods solve this task using a sequence-to-sequence model or using a graph-based model to encode RDF triples and to generate a text sequence. Nevertheless, these approaches fail to clearly model the local and global structural information between and within RDF triples. Moreover, the previous methods also face the non-negligible problem of low faithfulness of the generated text, which seriously affects the overall performance of these models. To solve these problems, we propose a model combining two new graph-augmented structural neural encoders to jointly learn both local and global structural information in the input RDF triples. To further improve text faithfulness, we innovatively introduce a reinforcement learning (RL) reward based on information extraction (IE). We first extract triples from the generated text using a pretrained IE model and regard the correct number of the extracted triples as the additional RL reward. Experimental results on two benchmark datasets demonstrate that our proposed model outperforms the state-of-the-art baselines, and the additional reinforcement learning reward does help to improve the faithfulness of the generated text.