Compositional Generalization for Multi-label Text Classification: A Data-Augmentation Approach
Despite significant advancements in multi-label text classification, the ability of existing models to generalize to novel and seldom-encountered complex concepts, which are compositions of elementary ones, remains underexplored. This research addresses this gap. By creating unique data splits across three benchmarks, we assess the compositional generalization ability of existing multi-label text classification models. Our results show that these models often fail to generalize to compositional concepts encountered infrequently during training, leading to inferior performance on tests with these new combinations. To address this, we introduce a data augmentation method that leverages two innovative text generation models designed to enhance the classification models' capacity for compositional generalization. Our experiments show that this data augmentation approach significantly improves the compositional generalization capabilities of classification models on our benchmarks, with both generation models surpassing other text generation baselines.
Code (1)
Tasks
ClassificationData AugmentationMulti Label Text ClassificationMulti-Label Text Classificationtext-classificationText ClassificationText GenerationSimilar Papers 제목 키워드 기반
Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text Generation
Compositional generalization, representing the model's ability to generate text with new attribute combinations obtained by recombining single attributes from the training data, is a crucial property for multi-aspect con…
AttributeBenchmarkingMeta-LearningText GenerationImproving Compositional Generalization in Classification Tasks via Structure Annotations
Compositional generalization is the ability to generalize systematically to a new data distribution by combining known components. Although humans seem to have a great ability to generalize compositionally, state-of-the-…
ClassificationTowards Understanding the Relationship between In-context Learning and Compositional Generalization
According to the principle of compositional generalization, the meaning of a complex expression can be understood as a function of the meaning of its parts and of how they are combined. This principle is crucial for huma…
Few-Shot LearningIn-Context LearningInductive BiasCrossMed: A Multimodal Cross-Task Benchmark for Compositional Generalization in Medical Imaging
Recent advances in multimodal large language models have enabled unified processing of visual and textual inputs, offering promising applications in general-purpose medical AI. However, their ability to generalize compos…
Visual Question AnsweringIndependent Prototype Propagation for Zero-Shot Compositionality
Humans are good at compositional zero-shot reasoning; someone who has never seen a zebra before could nevertheless recognize one when we tell them it looks like a horse with black and white stripes. Machine learning syst…
AttributeCompositional Zero-Shot Learning