Text Generation from Knowledge Graphs with Graph Transformers

by   Rik Koncel-Kedziorski, et al.

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.


page 1

page 2

page 3

page 4


Investigating Pretrained Language Models for Graph-to-Text Generation

Graph-to-text generation, a subtask of data-to-text generation, aims to ...

Modeling Graph Structure via Relative Position for Better Text Generation from Knowledge Graphs

We present a novel encoder-decoder architecture for graph-to-text genera...

R2D2: Relational Text Decoding with Transformers

We propose a novel framework for modeling the interaction between graphi...

A Hierarchical Model for Data-to-Text Generation

Transcribing structured data into natural language descriptions has emer...

Evidence-Aware Inferential Text Generation with Vector Quantised Variational AutoEncoder

Generating inferential texts about an event in different perspectives re...

Towards Generating Long and Coherent Text with Multi-Level Latent Variable Models

Variational autoencoders (VAEs) have received much attention recently as...

Multi-Document Scientific Summarization from a Knowledge Graph-Centric View

Multi-Document Scientific Summarization (MDSS) aims to produce coherent ...