Challenge: Unmeasured or latent confounders can bias causal estimates and this has motivated interest in measuring potential confounder from observed text.
Approach: They propose to use text to measure potential confounders in a way that allows for a rich measurement of multiple confounder variables.
Outcome: The proposed method is based on an individual’s entire history of social media posts or the content of a news article.

Similar Papers

Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond (2022.tacl-1)

Copied to clipboard

Challenge: causality has not had the same importance in natural language processing, says aaron e. smith . he says research on causality in NLP remains scattered across domains without unified definitions .
Approach: They propose to consolidate research on causality in NLP across academic areas . they explore potential uses of causal inference to improve robustness, fairness, interpretability .
Outcome: The proposed method is a unified overview of causal inference for the NLP community.
Causal Inference from Text: Unveiling Interactions between Variables (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for estimating causal effects from text only account for latent covariates that affect both treatment and outcome.
Approach: They propose to disentangle non-confounding covariates from text to minimize selection bias . they conduct experiments on two different treatment factors under various scenarios .
Outcome: The proposed model outperforms strong baselines on earnings call transcripts . the proposed model is based on a randomized controlled trial .
Challenges of Using Text Classifiers for Causal Inference (D18-1)

Copied to clipboard

Challenge: a number of scientific analyses focus on low-dimensional structured data, but text classifiers can be used to produce structured variables.
Approach: They propose to use text classifiers to conduct causal analyses on simulated and Yelp data.
Outcome: The proposed method can be used on simulated and Yelp data.
A Review of Dataset and Labeling Methods for Causality Extraction (2020.coling-main)

Copied to clipboard

Challenge: Existing methods for causal relationship extraction are limited and lack of unified methods hinder progress in the field.
Approach: They propose to summarize existing methods and propose a new causal sequence label method . they propose to use multiple candidate causal label sequences according to label controversy .
Outcome: The proposed method summarises existing methods and explores their practicability and extensibility from multiple perspectives.
Conceptualizing Treatment Leakage in Text-based Causal Inference (2022.naacl-main)

Copied to clipboard

Challenge: Existing methods to control for text-based confounders rely on assumption that there is no treatment leakage . prior literature has assumed that documents only contain information about confounder, but not about treatment assignment.
Approach: They define the treatment leakage problem and propose methods to mitigate it . they remove treatment-related signal from text in a pre-processing step .
Outcome: The proposed method can mitigate the problem of treatment leakage by removing the treatment-related signal from the text.
DoubleLingo: Causal Estimation with Large Language Models (2024.naacl-short)

Copied to clipboard

Challenge: Existing methods for causal estimation are inadequate for noisy text data.
Approach: They propose to use LLM-based nuisance models to estimate causal effects from non-randomized data using assumptions about the underlying data distribution.
Outcome: The proposed method reduces the relative absolute error by 10.4% over existing methods on the best available dataset.
CausalNLP Tutorial: An Introduction to Causality for Natural Language Processing (2022.emnlp-tutorials)

Copied to clipboard

Challenge: Establishing causal relationships is a fundamental goal of scientific research . lack of clear definitions, notations, benchmark datasets, and challenges remains .
Approach: They introduce the fundamentals of causal discovery and causal effect estimation to the natural language processing audience and provide an overview of causal perspectives to NLP problems.
Outcome: This tutorial introduces the fundamentals of causal discovery and causal effect estimation to the natural language processing audience and provides an overview of causal perspectives to NLP problems.
Causal Inference of Script Knowledge (2020.emnlp-main)

Copied to clipboard

Challenge: Prior work on script induction relied on correlation between instances of events in corpus . instead, we propose an approach based on causal effects between events .
Approach: They propose to use causal effects to induce scripts from text . they propose to compute a function that matches the intuition of what a script represents .
Outcome: The proposed method matches the intuition of what a script represents, the authors show .
Causal Inference with Large Language Model: A Survey (2025.findings-naacl)

Copied to clipboard

Challenge: Existing causal inference frameworks do not match human judgment in several key areas, such as domain knowledge, logical inference, and cultural context.
Approach: They propose to apply large language models to causal inference tasks . they summarize the main causal problems and approaches and compare their results .
Outcome: The proposed methods are compared with traditional methods in healthcare, finance, and economics.
Causal Matching with Text Embeddings: A Case Study in Estimating the Causal Effects of Peer Review Policies (2023.findings-acl)

Copied to clipboard

Challenge: Using a method that uses text embeddings, we find that human judges prefer manuscript matches from our method in 70% of cases.
Approach: They propose to use text embeddings to integrate a method to estimate the causal effects of peer review policies in publication venues that shift policies from single-blind to double-blinded.
Outcome: The proposed method is compared with a widely-used method of stratified propensity score matching and a baseline of randomly selected matches.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations