Substructure Substitution: Structured Data Augmentation for NLP
We study a family of data augmentation methods, substructure substitution (SUB2), for natural language processing (NLP) tasks. SUB2 generates new examples by substituting substructures (e.g., subtrees or subsequences) with ones with the same label, which can be applied to many structured NLP tasks such as part-of-speech tagging and parsing. For more general tasks (e.g., text classification) which do not have explicitly annotated substructures, we present variations of SUB2 based on constituency parse trees, introducing structure-aware data augmentation methods to general NLP tasks. For most cases, training with the augmented dataset by SUB2 achieves better performance than training with the original training set. Further experiments show that SUB2 has more consistent performance than other investigated augmentation methods, across different tasks and sizes of the seed dataset.
Code (0)
등록된 구현이 없습니다.
Tasks
Data AugmentationPart-Of-Speech Taggingtext-classificationText ClassificationSimilar Papers 제목 키워드 기반
Improving the accuracy and generalizability of molecular property regression models with a substructure-substitution-rule-informed framework
Artificial Intelligence (AI)-aided drug discovery is an active research field, yet AI models often exhibit poor accuracy in regression tasks for molecular property prediction, and perform catastrophically poorly for out-…
Molecular Property PredictionDrug DiscoveryLearning to Substitute Spans towards Improving Compositional Generalization
Despite the rising prevalence of neural sequence models, recent empirical evidences suggest their deficiency in compositional generalization. One of the current de-facto solutions to this problem is compositional data au…
Data AugmentationInductive BiasSystematic GeneralizationMolecular Substructure-Aware Network for Drug-Drug Interaction Prediction
Concomitant administration of drugs can cause drug-drug interactions (DDIs). Some drug combinations are beneficial, but other ones may cause negative effects which are previously unrecorded. Previous works on DDI predict…
Equivariant Contrastive Learning for Sequential Recommendation
Contrastive learning (CL) benefits the training of sequential recommendation models with informative self-supervision signals. Existing solutions apply general sequential data augmentation strategies to generate positive…
Contrastive LearningData AugmentationSequential RecommendationSGOOD: Substructure-enhanced Graph-Level Out-of-Distribution Detection
Graph-level representation learning is important in a wide range of applications. Existing graph-level models are generally built on i.i.d. assumption for both training and testing graphs. However, in an open world, mode…
Out-of-Distribution DetectionRepresentation Learning