Using Text-Based Representations of Knowledge Graphs to Improve the Consistency of Generated Text

Loading...
Thumbnail Image

Persistent link to this item

Statistics
View Statistics

Journal Title

Journal ISSN

Volume Title

Title

Using Text-Based Representations of Knowledge Graphs to Improve the Consistency of Generated Text

Alternative title

Published Date

2023-01

Publisher

Type

Thesis or Dissertation

Abstract

Knowledge-enhanced language models in Natural Language Processing (NLP) have demonstrated in recent years that they are effective in many applications. This work attempts to show that knowledge-enhanced language models can be used to produce outputs that are not only more consistent with the information that is already known, but are also more plausible given other known information. In order to do so, this work introduces a modified Bidirectional and AutoRegressive Transformers (BART) model\cite{Lewis2020BARTDS}, which is modified to use a Text-based Representation of a Knowledge Graph (BART-TRKG). Experimental results demonstrate that this approach, when evaluated on a custom dataset, is able to improve upon the performance of a plain BART model in consistency and plausibility, as well as on other metrics according to a variety of human evaluators.

Keywords

Description

University of Minnesota M.S. thesis. January 2023. Major: Computer Science. Advisor: Maria Gini. 1 computer file (PDF); vii, 45 pages.

Related to

Replaces

License

Series/Report Number

Funding information

Isbn identifier

Doi identifier

Previously Published Citation

Other identifiers

Suggested citation

Lucke, Michael. (2023). Using Text-Based Representations of Knowledge Graphs to Improve the Consistency of Generated Text. Retrieved from the University Digital Conservancy, https://hdl.handle.net/11299/253403.

Content distributed via the University Digital Conservancy may be subject to additional license and use restrictions applied by the depositor. By using these files, users agree to the Terms of Use. Materials in the UDC may contain content that is disturbing and/or harmful. For more information, please see our statement on harmful content in digital repositories.