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

Abstract

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.

10 pages, 6 figures, EMNLP 2018

References in corpus (3)

• Sequence to Sequence Learning with Neural Networks
• SEE: Syntax-aware Entity Embedding for Neural Relation Extraction
• CANDiS: Coupled & Attention-Driven Neural Distant Supervision

Cited by in corpus (6)

• Deep Neural Approaches to Relation Triplets Extraction: A Comprehensive Survey
• Connecting Language and Knowledge with Heterogeneous Representations for Neural Relation Extraction
• Deep Neural Networks for Relation Extraction
• Integrating Relation Constraints with Neural Relation Extractors
• Exploring the Suitability of Semantic Spaces as Word Association Models for the Extraction of Semantic Relationships
• SENT: Sentence-level Distant Relation Extraction via Negative Training