Good-Enough Compositional Data Augmentation
원문 초록
We propose a simple data augmentation protocol aimed at providing a compositional inductive bias in conditional and unconditional sequence models. Under this protocol, synthetic training examples are constructed by taking real training examples and replacing (possibly discontinuous) fragments with other fragments that appear in at least one similar environment. The protocol is model-agnostic and useful for a variety of tasks. Applied to neural sequence-to-sequence models, it reduces error rate by as much as 87% on diagnostic tasks from the SCAN dataset and 16% on a semantic parsing task. Applied to n-gram language models, it reduces perplexity by roughly 1% on small corpora in several languages.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
AI-Enhanced Pediatric Pneumonia Detection: A CNN-Based Approach Using Data Augmentation and Generative Adversarial Networks (GANs)
Iceberg: Enhancing HLS Modeling with Synthetic Data
Evolution without Large Models: Training Language Model with Task Principles
Robust Training with Data Augmentation for Medical Imaging Classification
Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition
BlastDiffusion: A Latent Diffusion Model for Generating Synthetic Embryo Images to Address Data Scarcity in In Vitro Fertilization
토론
이 논문과 연결된 포럼 글이 아직 없습니다.