Learning coherent narratives from text-based knowledge graphs

Simple item page
dc.contributor.advisorErk, Katrin
dc.creatorTomkovich, Alexander Richard
dc.creator.orcid0000-0003-4912-3899
dc.date.accessioned2021-09-07T20:53:59Z
dc.date.available2021-09-07T20:53:59Z
dc.date.created2020-08
dc.date.issued2020-09-14
dc.date.submittedAugust 2020
dc.date.updated2021-09-07T20:53:59Z
dc.description.abstractAlthough efforts to reason over large-scale knowledge graphs have continued to gain traction over the last decade, document-level knowledge graphs still remain underexplored. In this work, we build on previous efforts in narrative cloze and one-class clustering to develop a system which takes in as input mixtures of text-based knowledge graphs that meet at shared entity/event nodes and aims to expand subgraphs which correspond to coherent narratives within those mixtures. We develop two main types of synthetic data with two associated tasks: "graph salads" are mixtures of text-based KGs generated from distinct documents which require our inference models to iteratively add a sequence of graph pieces to a starting narrative, while "cloze-style" instances are mixtures of text-based KGs from distinct documents which require the admission/rejection of a single graph piece. We develop corresponding neural models which leverage graph convolutional networks and an attention mechanism to perform inference over these graphs. We show that our data is learnable, and offer suggestions for future improvement of both our data generation procedures and model architectures.
dc.description.departmentComputer Science
dc.format.mimetypeapplication/pdf
dc.identifier.urihttps://hdl.handle.net/2152/87504
dc.identifier.urihttp://dx.doi.org/10.26153/tsw/14448
dc.language.isoen
dc.subjectNarrative cloze
dc.subjectNarrative coherence
dc.subjectKnowledge graphs
dc.subjectGraph convolutional networks
dc.titleLearning coherent narratives from text-based knowledge graphs
dc.typeThesis
dc.type.materialtext
thesis.degree.departmentComputer Sciences
thesis.degree.disciplineComputer Science
thesis.degree.grantorThe University of Texas at Austin
thesis.degree.levelMasters
thesis.degree.nameMaster of Science in Computer Sciences

Access full-text files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
TOMKOVICH-THESIS-2020.pdf
Size:
3.06 MB
Format:
Adobe Portable Document Format
Download

License bundle

Now showing 1 - 2 of 2
No Thumbnail Available
Name:
PROQUEST_LICENSE.txt
Size:
4.45 KB
Format:
Plain Text
Description:
Download
No Thumbnail Available
Name:
LICENSE.txt
Size:
1.84 KB
Format:
Plain Text
Description:
Download

Collections

UT Electronic Theses and Dissertations