no code implementations • 6 Mar 2024 • Jingru Zhu, Ya Guo, Geng Sun, Liang Hong, Jie Chen
Then, a causal prototypical contrast module is used to learn domain invariant causal features.
no code implementations • 4 Feb 2024 • Chong Zhang, Yixi Zhao, Chenshu Yuan, Yi Tu, Ya Guo, Qi Zhang
Therefore, we claim the necessary standards for an ideal benchmark to evaluate the information extraction ability of PTLMs.
1 code implementation • 17 Oct 2023 • Chong Zhang, Ya Guo, Yi Tu, Huan Chen, Jinyang Tang, Huijia Zhu, Qi Zhang, Tao Gui
However, BIO-tagging scheme relies on the correct order of model inputs, which is not guaranteed in real-world NER on scanned VrDs where text are recognized and arranged by OCR systems.
Ranked #1 on Entity Linking on FUNSD
no code implementations • 30 May 2023 • Yi Tu, Ya Guo, Huan Chen, Jinyang Tang
LayoutMask can enhance the interactions between text and layout modalities in a unified model and produce adaptive and robust multi-modal representations for downstream tasks.
Ranked #1 on Semantic entity labeling on FUNSD
1 code implementation • 16 Aug 2022 • Jingru Zhu, Ya Guo, Geng Sun, Libo Yang, Min Deng, Jie Chen
This study proposes a novel unsupervised domain adaptation semantic segmentation network (MemoryAdaptNet) for the semantic segmentation of HRS imagery.
no code implementations • 7 Feb 2022 • Yazhong Si, Fan Yang, Ya Guo, Wei zhang, Yipu Yang
In this paper, we presented a comprehensive perceptual study and analysis of real-world sand dust images, then constructed a Sand-dust Image Reconstruction Benchmark (SIRB) for training Convolutional Neural Networks (CNNs) and evaluating algorithms performance.