Show simple item record

dc.contributor.authorVezvaei, Alireza
dc.date.accessioned2022-09-16 20:18:52 (GMT)
dc.date.issued2022-09-16
dc.date.submitted2022-09-06
dc.identifier.urihttp://hdl.handle.net/10012/18750
dc.description.abstractKnowledge Graphs (KGs) have many applications, specifically in information retrieval and question answering. Community projects are conducted for building large-scale KGs with crowdsourcing, but building KGs with this approach is costly and sometimes infeasible. Considering the rapidly growing amount of unstructured text on the Web, we highly need systems for automatic KG generation. We propose KG-Pipeline, a general-purpose end-to-end pipeline designed for automatically constructing KGs from unstructured text documents. We leverage state-of-the-art NLP models for implementing various components of the pipeline. We also utilize our generated KGs in Question Answering (QA) and evaluate the performance of our system on a QA benchmark, comparing it to previous work and an information retrieval baseline model.en
dc.language.isoenen
dc.publisherUniversity of Waterlooen
dc.subjectknowledge graphen
dc.subjectquestion answeringen
dc.subjectinformation extractionen
dc.subjectNLPen
dc.subjectnatural language processingen
dc.titleKG-Pipeline: An Automated Knowledge Graph Generation Frameworken
dc.typeMaster Thesisen
dc.pendingfalse
uws-etd.degree.departmentDavid R. Cheriton School of Computer Scienceen
uws-etd.degree.disciplineComputer Scienceen
uws-etd.degree.grantorUniversity of Waterlooen
uws-etd.degreeMaster of Mathematicsen
uws-etd.embargo.terms4 monthsen
uws.contributor.advisorGolab, Lukasz
uws.contributor.affiliation1Faculty of Mathematicsen
uws.published.cityWaterlooen
uws.published.countryCanadaen
uws.published.provinceOntarioen
uws-etd.embargo2023-01-14T20:18:52Z
uws.typeOfResourceTexten
uws.peerReviewStatusUnrevieweden
uws.scholarLevelGraduateen


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record


UWSpace

University of Waterloo Library
200 University Avenue West
Waterloo, Ontario, Canada N2L 3G1
519 888 4883

All items in UWSpace are protected by copyright, with all rights reserved.

DSpace software

Service outages