Relation-based Counterfactual Data Augmentation and Contrastive Learning for Robustifying Natural Language Inference Models
Although pre-trained language models show good performance on various natural language processing tasks, they often rely on non-causal features and patterns to determine the outcome. For natural language inference tasks, previous results have shown that even a model trained on a large number of data fails to perform well on counterfactually revised data, indicating that the model is not robustly learning the semantics of the classes. In this paper, we propose a method in which we use token-based and sentence-based augmentation methods to generate counterfactual sentence pairs that belong to each class, and apply contrastive learning to help the model learn the difference between sentence pairs of different classes with similar contexts. Evaluation results with counterfactually-revised dataset and general NLI datasets show that the proposed method can improve the performance and robustness of the NLI model.
Code (0)
등록된 구현이 없습니다.
Tasks
Contrastive LearningcounterfactualData AugmentationNatural Language InferenceRelationSentenceMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Improving the Robustness of Dense Retrievers Against Typos via Multi-Positive Contrastive Learning
Dense retrieval has become the new paradigm in passage retrieval. Despite its effectiveness on typo-free queries, it is not robust when dealing with queries that contain typos. Current works on improving the typo-robustn…
Contrastive LearningData AugmentationPassage RetrievalRetrievalRetrieval-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+5Counterfactual contrastive learning: robust representations via causal image synthesis
Contrastive pretraining is well-known to improve downstream task performance and model generalisation, especially in limited label settings. However, it is sensitive to the choice of augmentation pipeline. Positive pairs…
Contrastive LearningcounterfactualCounterfactual InferenceImage GenerationLearning to Contrast the Counterfactual Samples for Robust Visual Question Answering
In the task of Visual Question Answering (VQA), most state-of-the-art models tend to learn spurious correlations in the training set and achieve poor performance in out-of-distribution test data. Some methods of generati…
Contrastive LearningcounterfactualDiagnosticQuestion Answering+2AC2L-GAD: Active Counterfactual Contrastive Learning for Graph Anomaly Detection
Graph anomaly detection aims to identify abnormal patterns in networks, but faces significant challenges from label scarcity and extreme class imbalance. While graph contrastive learning offers a promising unsupervised s…
Graph Anomaly DetectionContrastive Learning