Modeling Global and Local Node Contexts for Text Generation from Knowledge Graphs

Abstract

Recent graph-to-text models generate text from graph-based data using either global or local aggregation to learn node representations. Global node encoding allows explicit communication between two distant nodes, thereby neglecting graph topology as all nodes are directly connected. In contrast, local node encoding considers the relations between neighbor nodes capturing the graph structure, but it can fail to capture long-range relations. In this work, we gather both encoding strategies, proposing novel neural models which encode an input graph combining both global and local node contexts, in order to learn better contextualized node embeddings. In our experiments, we demonstrate that our approaches lead to significant improvements on two graph-to-text datasets achieving BLEU scores of 18.01 on AGENDA dataset, and 63.69 on the WebNLG dataset for seen categories, outperforming state-of-the-art models by 3.7 and 3.1 points, respectively.

Accepted for publication in Transactions of the Association for Computational Linguistics (TACL), 2020; Author's final version; pre-MIT Press publication version

References in corpus (10)

• Semi-Supervised Classification with Graph Convolutional Networks
• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• Inductive Representation Learning on Large Graphs
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Fast Graph Representation Learning with PyTorch Geometric
• Representation Learning on Graphs with Jumping Knowledge Networks
• Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning
• Step-by-Step: Separating Planning from Realization in Neural Data-to-Text Generation
• Structural Neural Encoders for AMR-to-text Generation
• Modeling Graph Structure in Transformer for Better AMR-to-Text Generation

Cited by in corpus (6)

• Stage-wise Fine-tuning for Graph-to-Text Generation
• TrICy: Trigger-guided Data-to-text Generation with Intent aware Attention-Copy
• Mind the Labels: Describing Relations in Knowledge Graphs With Pretrained Models
• Generating Diverse Descriptions from Semantic Graphs
• JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs
• Generating Faithful Text From a Knowledge Graph with Noisy Reference Text