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

Vashishth, Shikhar ; Joshi, Rishabh ; Prayaga, Sai Suman ; Bhattacharyya, Chiranjib ; Talukdar, Partha P. (2018) RESIDE: Improving Distantly-Supervised Neural Relation Extraction using Side Information CoRR, abs/18 .

[img] PDF
1MB

Official URL: http://arxiv.org/abs/1812.04361

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.

Item Type:Article
Source:Copyright of this article belongs to arXiv
ID Code:127685
Deposited On:13 Oct 2022 11:00
Last Modified:13 Oct 2022 11:00

Repository Staff Only: item control page