Graph

Process engineering

Knowledge base

ENCODE

Gene

Data mining

Geodesy

Extractor

Machine learning

Engineering

Relationship extraction

Benchmark (surveying)

Artificial intelligence

Geography

Relation (database)

Set (abstract data type)

Chemistry

Information extraction

Programming language

Natural language processing

Code (set theory)

Computer science

Theoretical computer science

Source code

Artificial neural network

Biochemistry

Distantly-supervised Relation Extraction (RE) methods train an extractor by automatically aligning relation instances in a Knowledge Base (KB) with unstructured text. In addition to relation instances, KBs often contain other relevant side information, such as aliases of relations (e.g., founded and co-founded are aliases for the relation founderOfCompany). RE models usually ignore such readily available side information. In this paper, we propose RESIDE, a distantly-supervised neural relation extraction method which utilizes additional side information from KBs for improved relation extraction. It uses entity type and relation alias information for imposing soft constraints while predicting relations. RESIDE employs Graph Convolution Networks (GCN) to encode syntactic information from text and improves performance even when limited side information is available. Through extensive experiments on benchmark datasets, we demonstrate RESIDE's effectiveness. We have made RESIDE's source code available to encourage reproducible research.

RESIDE: Improving Distantly-Supervised Neural Relation Extraction using Side Information