Less is More: Attention Supervision with Counterfactuals for Text Classification
We aim to leverage human and machine intelligence together for attention supervision. Specifically, we show that human annotation cost can be kept reasonably low, while its quality can be enhanced by machine self-supervision. Specifically, for this goal, we explore the advantage of counterfactual reasoning, over associative reasoning typically used in attention supervision. Our empirical results show that this machine-augmented human attention supervision is more effective than existing methods requiring a higher annotation cost, in text classification tasks, including sentiment analysis and news categorization.
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationcounterfactualCounterfactual ReasoningGeneral ClassificationSentiment Analysistext-classificationText ClassificationSimilar Papers 제목 키워드 기반
Causal Counterfactuals Reconsidered
I develop a novel semantics for probabilities of counterfactuals that generalizes the standard Pearlian semantics: it applies to probabilistic causal models that cannot be extended into realistic structural causal models…
Retrieval-guided Counterfactual Generation for QA
Deep NLP models have been shown to be brittle to input perturbations. Recent work has shown that data augmentation using counterfactuals --- i.e. minimally perturbed inputs --- can help ameliorate this weakness. We focus…
counterfactualData AugmentationDiversityQuestion Answering+5Retrieval-guided Counterfactual Generation for QA
Deep NLP models have been shown to learn spurious correlations, leaving them brittle to input perturbations. Recent work has shown that counterfactual or contrastive data -- i.e. minimally perturbed inputs -- can reveal …
counterfactualData AugmentationDiversityQuestion Answering+5Hierarchical Variational Autoencoder for Visual Counterfactuals
Conditional Variational Auto Encoders (VAE) are gathering significant attention as an Explainable Artificial Intelligence (XAI) tool. The codes in the latent space provide a theoretically sound way to produce counterfact…
Explainable artificial intelligenceExplainable Artificial Intelligence (XAI)Learning More from Less: Exploiting Counterfactuals for Data-Efficient Chart Understanding
Vision-Language Models (VLMs) have demonstrated remarkable progress in chart understanding, largely driven by supervised fine-tuning (SFT) on increasingly large synthetic datasets. However, scaling SFT data alone is inef…