ACL Findings2026
Text Embedding as Treatment: A Meta Causal Approach for Robust Sentiment Classification
Fengxiang Cheng, Chuan Zhou, Xiang Li, Haoxuan Li, Wen-li Wang, Jinkun Chen, Mingming Gong, Kun Zhang
Abstract
Sentiment classification is a crucial task in natural language processing (NLP). To mitigate the spurious correlation, the causal word identification method estimates the impact of treatment words on sentence sentiment and removes those with low treatment effects. However, previous works regard the presence or absence of a specific word in a sentence as a binary treatment. This approach limits the generalizability to novel words and the robustness of low-frequency words. To bridge this gap, we propose a meta-causal approach that achieves causal word identification for arbitrary words with a single training task. Specifically, we begin by clustering contexts based on their embeddings obtained from a pre-trained language model. Subsequently, for each cluster, a representation and multi-head prediction networks are trained to estimate the treatment effect of each word to distinguish causally related words from spuriously correlated ones. The trained word classifier is then used to give weights for different words to train a more robust and generalizable sentiment classification model. Extensive experiments on public datasets demonstrate the effectiveness of our method in identifying causal words and improving the performance of sentiment classification.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- Treatment Effect Estimation with Disentangled Latent Factors cites Learning Disentangled Representations for CounterFactual Regression
- Robustness to Spurious Correlations in Text Classification via Automatically Generated Counterfactuals cites Learning The Difference That Makes A Difference With Counterfactually-Augmented Data
Builds on12
- ALBERT: A Lite BERT for Self-supervised Learning of Language RepresentationsZhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel et al.ICLR 2020 · 7,418 citations
- Learning The Difference That Makes A Difference With Counterfactually-Augmented DataDivyansh Kaushik, Eduard H. Hovy, Zachary Chase LiptonICLR 2020 · 625 citations
- Learning Disentangled Representations for CounterFactual RegressionNegar Hassanpour, Russell GreinerICLR 2020 · 176 citations
- Treatment Effect Estimation with Disentangled Latent FactorsWeijia Zhang, Lin Liu, Jiuyong LiAAAI 2021 · 115 citations
- Robustness to Spurious Correlations in Text Classification via Automatically Generated CounterfactualsZhao Wang, Aron CulottaAAAI 2021 · 114 citations
Related papers
- Mitigating Spurious Correlations via Counterfactual Contrastive LearningFengxiang Cheng, Chuan Zhou, Xiang Li, Alina Leidinger et al.EMNLP Findings 2025
- Identifying spurious correlations for robust text classificationZhao Wang, Aron CulottaEMNLP Findings 2020 · 60 citations
- Counterfactual Reasoning for Out-of-distribution Multimodal Sentiment AnalysisTeng Sun, Wenjie Wang, Liqiang Jing, Yiran Cui et al.ACM MM 2022 · 65 citations
- Controlling Learned Effects to Reduce Spurious Correlations in Text ClassifiersParikshit Bansal, Amit SharmaACL 2023 · 1 citation
- Reducing Sentiment Bias in Pre-trained Sentiment Classification via Adaptive Gumbel AttackJiachen Tian, Shizhan Chen, Xiaowang Zhang, Xin Wang et al.AAAI 2023 · 5 citations
