Element Intervention for Open Relation Extraction
This work addresses instability in OpenRE for NLP researchers, offering a novel causal approach to improve clustering of relation instances.
The paper tackles instability and collapse in Open Relation Extraction models by addressing spurious correlations from entities and context to relation types through a causal view and element intervention. Experimental results show the methods outperform previous state-of-the-art and are robust across datasets.
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.