eduzhai > Socail Sciences > Education >

A Framework Using Active Learning to Rapidly Perform Named Entity Extraction and Relation Recognition for Science and Technology Knowledge Graph

  • Save

... pages left unread,continue reading

Document pages: 11 pages

Abstract: Construct a knowledge graph is time-consuming and the knowledge graph inthe scientific domain requires extremely high labor costs due to it requireshigh prior knowledge to extract knowledge from resources. To build a scientificresearch knowledge graph, the most of input are papers, patent, the descriptionof their project and some national program (such as National High TechnologyResearch and Development Program of China, Major State Basic ResearchDevelopment Program of China, General Program, Key Program and Major Program)which all of them are unstructured data, that make human participation aremostly necessary to measure the quality. In thispaper, we design and proposed a framework using active learning; this frameworkcan be used to extract entity and relation from unstructured science andtechnology research data. This framework combines the human and machine learning approach together,which is active learning, to help user extract entity from those unstructureddata with less time cost. By using those data to construct a CKG as annotationlabel, it further implements active learning tools and helps the expert torapidly annotate the data with high accuracy. Those knowledge graph constructedby this framework can be used to finding similar research area, finding similarresearchers, finding popular research areas and so on.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×