Uncovering Main Causalities for Long-tailed Information Extraction

TL;DR

This paper introduces CFIE, a causal inference framework for information extraction that mitigates dataset bias and spurious correlations by leveraging structural causal models and counterfactual reasoning, improving robustness across multiple tasks.

Contribution

The paper proposes a novel counterfactual IE framework using a structural causal model to uncover true causal relations and reduce bias in information extraction tasks.

Findings

CFIE effectively reduces spurious correlations.

Improves robustness of IE models across datasets.

Outperforms baseline methods in experiments.

Abstract

Information Extraction (IE) aims to extract structural information from unstructured texts. In practice, long-tailed distributions caused by the selection bias of a dataset, may lead to incorrect correlations, also known as spurious correlations, between entities and labels in the conventional likelihood models. This motivates us to propose counterfactual IE (CFIE), a novel framework that aims to uncover the main causalities behind data in the view of causal inference. Specifically, 1) we first introduce a unified structural causal model (SCM) for various IE tasks, describing the relationships among variables; 2) with our SCM, we then generate counterfactuals based on an explicit language structure to better calculate the direct causal effect during the inference stage; 3) we further propose a novel debiasing approach to yield more robust predictions. Experiments on three IE tasks across five public datasets show the effectiveness of our CFIE model in mitigating the spurious correlation issues.