ABSTRACT
With the success of machine learning (ML) techniques, ML has already proved a tremendous potential to impact the foundations, algorithms, and models of several data management tasks, such as error detection, data quality assessment, data cleaning, and data integration. In Knowledge Graphs, part of the data preparation and cleaning processes, such as data linking, identity disambiguation, or missing value inference and completion could be automated by making a ML model “learn” and predict the matches routinely with different degrees of supervision. This talk will survey the recent trends of applying machine learning solutions to improve and facilitate Knowledge Graph curation and enrichment, as one of the most critical tasks impacting Web search and query-answering. Finally, the talk will discuss the next research challenges in the convergence of machine learning and management of Knowledge Graph evolution and preservation.
- Berti-Equille L., Scannapieco M. (2016). Quality of Web Data (Chapter). In the 2nd Edition of the book Data Quality: Concepts, Methodologies and Techniques, Springer, 2016Google Scholar
- Zaveri A., Maurino A., Berti-Equille L. (2014). Web Data Quality: Current State and New Challenges, Int. J. Semant. Web Inf. Syst.,10(2):1552-6283, IGI Global. Google ScholarDigital Library
- Paulheim H. (2017) Knowledge graph refinement: A survey of approaches and evaluation methods. Semantic Web 8 3 489-508.Google Scholar
- Paritosh P. (2018). The Missing Science of Knowledge Curation (Improving incentives for large-scale knowledge curation). In Companion of The Web Conference 2018, Lyon, France. Google ScholarDigital Library
Index Terms
- ML-Based Knowledge Graph Curation: Current Solutions and Challenges
Recommendations
Entity Disambiguation with Linkless Knowledge Bases
WWW '16: Proceedings of the 25th International Conference on World Wide WebNamed Entity Disambiguation is the task of disambiguating named entity mentions in natural language text and link them to their corresponding entries in a reference knowledge base (e.g. Wikipedia). Such disambiguation can help add semantics to plain ...
Knowledge Graph Augmentation with Entity Identification for Improving Knowledge Graph Completion Performance
PRICAI 2023: Trends in Artificial IntelligenceAbstractA knowledge graph often lacks some existent triples. Knowledge graph completion is a technique for complementing such triples and its performance can be improved by augmenting triples from other external databases. However, entity names often ...
A Comprehensive Survey on Automatic Knowledge Graph Construction
Automatic knowledge graph construction aims at manufacturing structured human knowledge. To this end, much effort has historically been spent extracting informative fact patterns from different data sources. However, more recently, research interest has ...
Comments