Proceedings of the Doctoral Consortium at the 16th International Semantic Web Conference

Cleaning Noisy Knowledge Graphs

My dissertation research is developing an approach to identify and explain errors in a knowledge graph constructed by extracting entities and relations from text. Information extraction systems can automatically construct knowledge graphs from a large collection of documents, which might be drawn from news articles, Web pages, social media posts or discussion forums. The language understanding task is challenging and current extraction systems introduce many kinds of errors. Previous work on improving the quality of knowledge graphs uses additional evidence from background knowledge bases or Web searches. Such approaches are dicult to apply when emerging entities are present and/or only one knowledge graph is available. In order to address the problem I am using multiple complementary techniques including entitylinking, common sense reasoning, and linguistic analysis.

  • 220013 bytes

knowledge graph, learning, natural language processing


CEUR Workshop Proceedings


Downloads: 1191 downloads

UMBC ebiquity