Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

4-2021

Abstract

News search tools help end users to identify relevant news stories. However, existing search approaches often carry out in a "black-box" process. There is little intuition that helps users understand how the results are related to the query. In this paper, we propose a novel news search framework, called NEWSLINK, to empower intuitive news search by using relationship paths discovered from open Knowledge Graphs (KGs). Specifically, NEWSLINK embeds both a query and news documents to subgraphs, called subgraph embeddings, in the KG. Their embeddings' overlap induces relationship paths between the involving entities. Two major advantages are obtained by incorporating subgraph embeddings into search. First, they enrich the search context, leading to robust results. Second, the relationship paths linking entities inter and intra news documents can help users better understand and digest the results for the given query. Through both human and automatic evaluations, we verify that NEWSLINK can help users understand the result-to-query relatedness, while its search quality is robust and outperforms many established search approaches, including Apache Lucene and a KG-powered query expansion approach, as well as popular deep learning models, Sentence-BERT (SBERT) and DOC2VEC.

Discipline

Databases and Information Systems | Data Storage Systems

Research Areas

Data Science and Engineering

Publication

Proceedings of 2021 IEEE 37th International Conference on Data Engineering, Chania, Greece, April 19-22

First Page

876

Last Page

887

ISBN

9781728191843

Identifier

10.1109/ICDE51399.2021.00081

Publisher

IEEE

City or Country

USA

Download

Share

COinS