Populating Web Scale Knowledge Graphs using Distantly Supervised Relation Extraction and Validation

TL;DR

This paper presents an automated, scalable system that uses deep learning and distant supervision to extend knowledge graphs from web data, significantly improving relation extraction accuracy without manual effort.

Contribution

The novel system combines relation extraction and knowledge base completion using deep learning, eliminating the need for hand-labeled data and domain adaptation.

Findings

50% error reduction in relation extraction

Up to 100% relative improvement in accuracy

Successful extension of DBPedia with Common Crawl data

Abstract

In this paper, we propose a fully automated system to extend knowledge graphs using external information from web-scale corpora. The designed system leverages a deep learning based technology for relation extraction that can be trained by a distantly supervised approach. In addition to that, the system uses a deep learning approach for knowledge base completion by utilizing the global structure information of the induced KG to further refine the confidence of the newly discovered relations. The designed system does not require any effort for adaptation to new languages and domains as it does not use any hand-labeled data, NLP analytics and inference rules. Our experiments, performed on a popular academic benchmark demonstrate that the suggested system boosts the performance of relation extraction by a wide margin, reporting error reductions of 50%, resulting in relative improvement of up to 100%. Also, a web-scale experiment conducted to extend DBPedia with knowledge from Common Crawl shows that our system is not only scalable but also does not require any adaptation cost, while yielding substantial accuracy gain.