Logic-Guided Data Augmentation and Regularization for Consistent Question Answering

2020-04-21 · ACL 2020 6 · Akari Asai, Hannaneh Hajishirzi

Many natural language questions require qualitative, quantitative or logical comparisons between two entities or events. This paper addresses the problem of improving the accuracy and consistency of responses to comparison questions by integrating logic rules and neural models. Our method leverages logical and linguistic knowledge to augment labeled training data and then uses a consistency-based regularizer to train the model. Improving the global consistency of predictions, our approach achieves large improvements over previous methods in a variety of question answering (QA) tasks including multiple-choice qualitative reasoning, cause-effect reasoning, and extractive machine reading comprehension. In particular, our method significantly improves the performance of RoBERTa-based models by 1-5% across datasets. We advance the state of the art by around 5-8% on WIQA and QuaRel and reduce consistency violations by 58% on HotpotQA. We further demonstrate that our approach can learn effectively from limited data.

📄 PDF Abstract BibTeX arXiv:2004.10157

Code (1)

AkariAsai/logic_guided_qa 공식 구현 pytorch

Tasks

Data Augmentation Machine Reading ComprehensionMultiple-choiceQuestion Answering Reading Comprehension

Adversarial cycle-consistent synthesis of cerebral microbleeds for data augmentation

2021-01-16 · Khrystyna Faryna, Kevin Koschmieder, Marcella M. Paul, Thomas van den Heuvel 외

We propose a novel framework for controllable pathological image synthesis for data augmentation. Inspired by CycleGAN, we perform cycle-consistent image-to-image translation between two domains: healthy and pathological…

Data Augmentation Image Generation Image-to-Image Translation Translation

Mask-Guided Attention Regulation for Anatomically Consistent Counterfactual CXR Synthesis

2026-03-04 · Zichun Zhang, Weizhi Nie, Honglin Guo, Yuting Su arxiv

Counterfactual generation for chest X-rays (CXR) aims to simulate plausible pathological changes while preserving patient-specific anatomy. However, diffusion-based editing methods often suffer from structural drift, whe…

Data Augmentation

Topological Regularization for Graph Neural Networks Augmentation

2021-04-03 · Rui Song, Fausto Giunchiglia, Ke Zhao, Hao Xu

The complexity and non-Euclidean structure of graph data hinder the development of data augmentation methods similar to those in computer vision. In this paper, we propose a feature augmentation method for graph nodes ba…

Data Augmentation Graph Neural Network Representation Learning

MedDiffuseMix: Preserving Diagnostic Evidence with Saliency-Aware Diffusion Medical Image Data Augmentatio

2026-06-25 · Teerath Kumar, Raja Vavekanand, Muhammad Turab arxiv

Limited data availability, class imbalance, and domain variability remain major barriers to reliable medical image classification. Conventional augmentation can improve training diversity but may distort diagnostically i…

Medical Image Classification Image Augmentation

Graph-Guided Dual-Level Augmentation for 3D Scene Segmentation

2025-07-30 · Hongbin Lin, Yifan Jiang, Juangui Xu, Jesse Jiaxi Xu 외 arxiv

3D point cloud segmentation aims to assign semantic labels to individual points in a scene for fine-grained spatial understanding. Existing methods typically adopt data augmentation to alleviate the burden of large-scale…

Point Cloud Segmentation Scene Segmentation Data Augmentation Scene Generation