Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Department of Computing | en_US |
| dc.creator | Zhao, Zihao | - |
| dc.identifier.uri | https://theses.lib.polyu.edu.hk/handle/200/11337 | - |
| dc.language | English | en_US |
| dc.publisher | Hong Kong Polytechnic University | en_US |
| dc.rights | All rights reserved | en_US |
| dc.title | Interactive ensemble learning for knowledge graph error detection | en_US |
| dcterms.abstract | Knowledge Graphs(KGs) now stand as the promising way to process relational data, embodying the relations among various realworld entities in the form of triplets. In the nature of things, to single out the anomalies in KGs has been a priority for us while the source of traditional knowledge extraction is not guaranteed. Recent years, many efforts have been laid on the KG error detection algorithms. However, there are not any general detection algorithms for all types of KGs and industrial scenarios for KG error detection, let alone the wellbelow performances of existing ones when it comes to real world demands. To solve this problem, human are qualified to recognize the normal triples and abnormal ones. Nevertheless, it is impratical for us to involve human efforts in the whole processes of detection for the big costs in extraordinary large size of different KGs, such kind of manual labeling will be extremely expensive. Meanwhile, advances in semisupervised learning and fewshot learning demonstrate that a small number of labels might greatly improve the learning performance. Thus, in this paper, we propose IKGED as an interactive KG error detection algorithm, exploring to leverage a small amount of human efforts to significantly advance the KG error detection. Specifically, to take full advantages of human efforts, in each iteration, we propose to enhance our querying strategy based on the feedback from human annotations. | en_US |
| dcterms.extent | vii, 62 pages : color illustrations | en_US |
| dcterms.isPartOf | PolyU Electronic Theses | en_US |
| dcterms.issued | 2021 | en_US |
| dcterms.educationalLevel | M.Sc. | en_US |
| dcterms.educationalLevel | All Master | en_US |
| dcterms.LCSH | Semantic networks (Information theory) | en_US |
| dcterms.LCSH | Knowledge management | en_US |
| dcterms.LCSH | Artificial intelligence | en_US |
| dcterms.LCSH | Hong Kong Polytechnic University -- Dissertations | en_US |
| dcterms.accessRights | restricted access | en_US |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 5869.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 1.48 MB | Adobe PDF | View/Open |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/11337