CoRI: Collective Relation Integration with Data Augmentation for Open Information Extraction

TL;DR

This paper introduces CoRI, a two-stage model for relation integration in knowledge graphs that uses collective prediction and data augmentation to improve accuracy in aligning free-text relations with KG relations.

Contribution

The paper presents a novel two-stage collective relation integration model with data augmentation, enhancing relation alignment accuracy in knowledge graphs.

Findings

CoRI significantly outperforms baselines in AUC metrics.

The collective model improves prediction consistency.

Data augmentation further boosts performance.

Abstract

Integrating extracted knowledge from the Web to knowledge graphs (KGs) can facilitate tasks like question answering. We study relation integration that aims to align free-text relations in subject-relation-object extractions to relations in a target KG. To address the challenge that free-text relations are ambiguous, previous methods exploit neighbor entities and relations for additional context. However, the predictions are made independently, which can be mutually inconsistent. We propose a two-stage Collective Relation Integration (CoRI) model, where the first stage independently makes candidate predictions, and the second stage employs a collective model that accesses all candidate predictions to make globally coherent predictions. We further improve the collective model with augmented data from the portion of the target KG that is otherwise unused. Experiment results on two datasets show that CoRI can significantly outperform the baselines, improving AUC from .677 to .748 and from .716 to .780, respectively.