首页|Research on Data Intelligence Discussed by a Researcher at University of Sao Pau lo (USP) (Applying a Context-based Method to Build a Knowledge Graph for the Blu e Amazon)
Research on Data Intelligence Discussed by a Researcher at University of Sao Pau lo (USP) (Applying a Context-based Method to Build a Knowledge Graph for the Blu e Amazon)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on data intelligence is t he subject of a new report. According to news reporting out of Sao Paulo, Brazil , by NewsRx editors, research stated, “ABSTRACT: Knowledge graphs are employed i n several tasks, such as question answering and recommendation systems, due to t heir ability to represent relationships between concepts.” The news reporters obtained a quote from the research from University of Sao Pau lo (USP): “Automatically constructing such a graphs, however, remains an unresol ved challenge within knowledge representation. To tackle this challenge, we prop ose CtxKG, a method specifically aimed at extracting knowledge graphs in a conte xt of limited resources in which the only input is a set of unstructured text do cuments. CtxKG is based on OpenIE (a relationship triple extraction method) and BERT (a language model) and contains four stages: the extraction of relationship triples directly from text; the identification of synonyms across triples; the merging of similar entities; and the building of bridges between knowledge graph s of different documents. Our method distinguishes itself from those in the curr ent literature (i) through its use of the parse tree to avoid the overlapping en tities produced by base implementations of OpenIE; and (ii) through its bridges, which create a connected network of graphs, overcoming a limitation similar met hods have of one isolated graph per document. We compare our method to two other s by generating graphs for movie articles from Wikipedia and contrasting them wi th benchmark graphs built from the OMDb movie database. Our results suggest that our method is able to improve multiple aspects of knowledge graph construction. ”
University of Sao Paulo (USP)Sao PauloBrazilSouth AmericaData IntelligenceMachine Learning
NETL
NSTL
