Uncovering Main Causalities for Long-tailed Information Extraction

09/11/2021
by   Guoshun Nan, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/11/2023

Unbiased Scene Graph Generation via Two-stage Causal Modeling

Despite the impressive performance of recent unbiased Scene Graph Genera...
research
09/28/2020

Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect

As the class size grows, maintaining a balanced dataset across many clas...
research
02/02/2022

Causal Inference Through the Structural Causal Marginal Problem

We introduce an approach to counterfactual inference based on merging in...
research
12/20/2022

Debiasing Stance Detection Models with Counterfactual Reasoning and Adversarial Bias Learning

Stance detection models may tend to rely on dataset bias in the text par...
research
10/13/2021

Causal Modelling of Heavy-Tailed Variables and Confounders with Application to River Flow

Confounding variables are a recurrent challenge for causal discovery and...
research
08/21/2023

Debiasing Counterfactuals In the Presence of Spurious Correlations

Deep learning models can perform well in complex medical imaging classif...
research
12/06/2022

Learning to Bound Counterfactual Inference in Structural Causal Models from Observational and Randomised Data

We address the problem of integrating data from multiple observational a...

Please sign up or login with your details

Forgot password? Click here to reset