Text Generation from Knowledge Graphs with Graph Transformers

Abstract

Generating texts which express complex ideas spanning multiple sentences requires a structured representation of their content (document plan), but these representations are prohibitively expensive to manually produce. In this work, we address the problem of generating coherent multi-sentence texts from the output of an information extraction system, and in particular a knowledge graph. Graphical knowledge representations are ubiquitous in computing, but pose a significant challenge for text generation techniques due to their non-hierarchical nature, collapsing of long-distance dependencies, and structural variety. We introduce a novel graph transforming encoder which can leverage the relational structure of such knowledge graphs without imposing linearization or hierarchical constraints. Incorporated into an encoder-decoder setup, we provide an end-to-end trainable system for graph-to-text generation that we apply to the domain of scientific text. Automatic and human evaluations show that our technique produces more informative texts which exhibit better document structure than competitive encoder-decoder methods.

arXiv commentAccepted as a long paper in NAACL 2019

References in corpus (5)

• Sequence to Sequence Learning with Neural Networks
• Sequence Transduction with Recurrent Neural Networks
• Modeling Coverage for Neural Machine Translation
• Get To The Point: Summarization with Pointer-Generator Networks
• Paper Abstract Writing through Editing Mechanism

Cited by in corpus (8)

• Ratatouille: A tool for Novel Recipe Generation
• KECRS: Towards Knowledge-Enriched Conversational Recommendation System
• FABULA: Intelligence Report Generation Using Retrieval-Augmented Narrative Construction
• FakeSwarm: Improving Fake News Detection with Swarming Characteristics
• Augmented Abstractive Summarization With Document-LevelSemantic Graph
• Graphmax for Text Generation
• Fact-level Extractive Summarization with Hierarchical Graph Mask on BERT
• GTAE: Graph-Transformer based Auto-Encoders for Linguistic-Constrained Text Style Transfer