paper-with-me

홈 › Papers

Solving SCAN Tasks with Data Augmentation and Input Embeddings

2021-09-01 · RANLP 2021 9 · Michal Auersperger, Pavel Pecina

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.

📄 PDF Abstract BibTeX

Code (1)

michal-au/scan-around-twice 공식 구현

Tasks

Data Augmentation

Similar Papers 제목 키워드 기반

Improving Robustness for Vision Transformer with a Simple Dynamic Scanning Augmentation

2023-11-01 · Shashank Kotyan, Danilo Vasconcellos Vargas

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

2020-12-07 · Mohammad Keshavarzi, Oladapo Afolabi, Luisa Caldas, Allen Y. Yang 외

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 Transfer

Intensity augmentation for domain transfer of whole breast segmentation in MRI

2019-09-05 · Linde S. Hesse, Grey Kuling, Mitko Veta, Anne L. Martel

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 Transfer

PolarMix: A General Data Augmentation Technique for LiDAR Point Clouds

2022-07-30 · Aoran Xiao, Jiaxing Huang, Dayan Guan, Kaiwen Cui 외

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+2

Improving Compositional Generalization in Math Word Problem Solving

2022-09-03 · Yunshi Lan, Lei Wang, Jing Jiang, Ee-Peng Lim

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