Solving SCAN Tasks with Data Augmentation and Input Embeddings
We address the compositionality challenge presented by the SCAN benchmark. Using data augmentation and a modification of the standard seq2seq architecture with attention, we achieve SOTA results on all the relevant tasks from the benchmark, showing the models can generalize to words used in unseen contexts. We propose an extension of the benchmark by a harder task, which cannot be solved by the proposed method.
Code (1)
Tasks
Data AugmentationSimilar Papers 제목 키워드 기반
Improving Robustness for Vision Transformer with a Simple Dynamic Scanning Augmentation
Vision Transformer (ViT) has demonstrated promising performance in computer vision tasks, comparable to state-of-the-art neural networks. Yet, this new type of deep neural network architecture is vulnerable to adversaria…
GenScan: A Generative Method for Populating Parametric 3D Scan Datasets
The availability of rich 3D datasets corresponding to the geometrical complexity of the built environments is considered an ongoing challenge for 3D deep learning methodologies. To address this challenge, we introduce Ge…
3D geometryData AugmentationStyle TransferIntensity augmentation for domain transfer of whole breast segmentation in MRI
The segmentation of the breast from the chest wall is an important first step in the analysis of breast magnetic resonance images. 3D U-nets have been shown to obtain high segmentation accuracy and appear to generalize w…
Domain AdaptationSegmentationStyle TransferPolarMix: A General Data Augmentation Technique for LiDAR Point Clouds
LiDAR point clouds, which are usually scanned by rotating LiDAR sensors continuously, capture precise geometry of the surrounding environment and are crucial to many autonomous detection and navigation tasks. Though many…
3D Object Detection3D Unsupervised Domain AdaptationData AugmentationDomain Adaptation+2Improving Compositional Generalization in Math Word Problem Solving
Compositional generalization refers to a model's capability to generalize to newly composed input data based on the data components observed during training. It has triggered a series of compositional generalization anal…
Data AugmentationMathMath Word Problem Solving