CANDiS: Coupled & Attention-Driven Neural Distant Supervision

TL;DR

This paper introduces CANDiS, a neural network model that improves distant supervision for relation extraction by leveraging inter-instance couplings and attention mechanisms, leading to better performance on benchmark datasets.

Contribution

CANDiS is a novel end-to-end neural model that exploits inter-instance couplings and attention for enhanced relation extraction under distant supervision.

Findings

CANDiS outperforms existing state-of-the-art methods on benchmark datasets.

The use of inter-instance couplings improves relation extraction accuracy.

Attention mechanisms effectively model the multi-instance nature of the task.

Abstract

Distant Supervision for Relation Extraction uses heuristically aligned text data with an existing knowledge base as training data. The unsupervised nature of this technique allows it to scale to web-scale relation extraction tasks, at the expense of noise in the training data. Previous work has explored relationships among instances of the same entity-pair to reduce this noise, but relationships among instances across entity-pairs have not been fully exploited. We explore the use of inter-instance couplings based on verb-phrase and entity type similarities. We propose a novel technique, CANDiS, which casts distant supervision using inter-instance coupling into an end-to-end neural network model. CANDiS incorporates an attention module at the instance-level to model the multi-instance nature of this problem. CANDiS outperforms existing state-of-the-art techniques on a standard benchmark dataset.