Element Intervention for Open Relation Extraction

TL;DR

This paper introduces an element intervention approach for open relation extraction, addressing instability caused by spurious correlations through causal modeling and interventions, leading to improved robustness and state-of-the-art performance.

Contribution

It formulates open relation extraction within a causal framework and proposes element interventions on entities and context to enhance model stability and accuracy.

Findings

Outperforms previous state-of-the-art methods on unsupervised datasets.

Demonstrates robustness across different datasets.

Addresses instability caused by spurious correlations.

Abstract

Open relation extraction aims to cluster relation instances referring to the same underlying relation, which is a critical step for general relation extraction. Current OpenRE models are commonly trained on the datasets generated from distant supervision, which often results in instability and makes the model easily collapsed. In this paper, we revisit the procedure of OpenRE from a causal view. By formulating OpenRE using a structural causal model, we identify that the above-mentioned problems stem from the spurious correlations from entities and context to the relation type. To address this issue, we conduct \emph{Element Intervention}, which intervenes on the context and entities respectively to obtain the underlying causal effects of them. We also provide two specific implementations of the interventions based on entity ranking and context contrasting. Experimental results on unsupervised relation extraction datasets show that our methods outperform previous state-of-the-art methods and are robust across different datasets.