Back to search

University of British Columbia

Discourse-guided text-generation from knowledge graphs and image scene graphs

Abstract

dc:description

This thesis introduces a discourse-guided approach for generating text from semi-structured data - knowledge graphs and image scene graphs. We provide a novel architecture that integrates discourse planning as an intermediary structuring step, with the objective of enhancing coherence, readability, and the overall quality of generated content. The proposed method reorders input graph nodes into a coherent discourse sequence prior to decoding, utilizing both Pointer Networks and Large Language Models (LLMs) to represent discourse structures. Our experiments focus on two distinct datasets - Agenda (scientific abstracts) and Visual Genome (image captioning) - illustrating that explicit discourse planning consistently enhances performance across standard natural language generation metrics and improves output quality as evaluated by both human and LLM-based assessments. This thesis presents a generalizable approach for integrating discourse structure into neural text generation systems and emphasizes the potential of large language models as both planners and evaluators in natural language generation tasks.

Degree

thesis:*
Name thesis:degree_name
Master of Science - MSc
Level thesis:degree_level
master's
Discipline thesis:degree_discipline
Computer Science
Grantor dc:publisher
University of British Columbia
Year dc:date
2025

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Ivanova, Inna
Contributors dc:contributor
  • Carenini, Giuseppe
  • Sigal, Leonid

Rights

dc:rights
Statement dc:rights
  • Attribution-NonCommercial-NoDerivatives 4.0 International
Language dc:language
eng

Identifiers

dc:identifier.*
Handle dc:identifier
http://hdl.handle.net/2429/91497

Chain of custody

source
Harvested from
University of British Columbia
Base URL
circle.library.ubc.ca/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
related terms
citation

Ivanova, Inna. Discourse-guided text-generation from knowledge graphs and image scene graphs. master's thesis, University of British Columbia, 2025. http://hdl.handle.net/2429/91497