Text Generation from Knowledge Graphs with Graph Transformers

By Rik Koncel-Kedziorski, Dhanush Bekal, Yi Luan, Mirella Lapata, Hannaneh Hajishirzi. 2019

363 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Natural Language Generation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Mohit Bansal
  2. Jianfeng Gao
  3. Yejin Choi
  4. Percy Liang
  5. Luke S. Zettlemoyer
  6. Noah A. Smith
  7. Graham Neubig
  8. Kyunghyun Cho

In Natural Language Generation

  1. Leonardo F. R. Ribeiro
  2. Hinrich Schütze
  3. Martin Schmitt
  4. Iryna Gurevych
  5. Oriol Vinyals
  6. Mohit Bansal
  7. Dong Yu
  8. Yejin Choi

Citations in the corpus