Text Generation from Knowledge Graphs with Graph Transformers

Rik Koncel-Kedziorski, Dhanush Bekal, Yi Luan, Maria Lapata, Hannaneh Hajishirzi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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 longdistance 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.
Original languageEnglish
Title of host publicationProceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics
EditorsJill Burstein, Christy Doran, Thamar Solorio
Place of PublicationMinneapolis, Minnesota
PublisherAssociation for Computational Linguistics (ACL)
Pages2284–2293
Number of pages10
Volume1
Publication statusPublished - 7 Jun 2019
Event2019 Annual Conference of the North American Chapter of the Association for Computational Linguistics - Minneapolis, United States
Duration: 2 Jun 20197 Jun 2019
https://naacl2019.org/

Conference

Conference2019 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Abbreviated titleNAACL-HLT 2019
CountryUnited States
CityMinneapolis
Period2/06/197/06/19
Internet address

Fingerprint Dive into the research topics of 'Text Generation from Knowledge Graphs with Graph Transformers'. Together they form a unique fingerprint.

Cite this