Finding textual description for paths in knowledge graphs

Abstract

We address the problem of finding a textual summary of facts within a path in a knowledge graph.Knowledge graphs are increasingly used in search engines and store data in the form of a Semantic Web structure making retrieval of information more accurate and efficient. Our solution would allow users to be given a small description of the search results increasing their comprehension of the facts presented to them. Ranking of passages is done using passage and document level evidence to find appropriate descriptions of multi-hop relationships. The source dataset used for our project is Wikipedia text corpus.