MatchVIE: Exploiting Match Relevancy between Entities for Visual Information Extraction
Authors: Guozhi Tang, Lele Xie, Lianwen Jin, Jiapeng Wang, Jingdong Chen, Zhen Xu, Qianying Wang, Yaqiang Wu, Hui Li
IJCAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Comprehensive experiments demonstrate that the proposed Match VIE can significantly outperform previous methods. Notably, to the best of our knowledge, Match VIE may be the first attempt to tackle the VIE task by modeling the relevancy between keys and values and it is a good complement to the existing methods. |
| Researcher Affiliation | Collaboration | 1School of Electronic and Information Engineering, South China University of Technology, China 2Guangdong Artificial Intelligence and Digital Economy Laboratory (Pazhou Lab), Guangzhou, China 3Ant Group, China 4Lenovo Research, China |
| Pseudocode | No | The paper describes the methodology using text and equations, but it does not include any clearly labeled pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not contain any statement about releasing source code for the methodology described, nor does it provide a link to a code repository. |
| Open Datasets | Yes | We conduct experiments on three real-world public datasets, whose statistics are given in Table 1. ... FUNSD[Jaume et al., 2019] is a public dataset of 199 fully annotated forms... EPHOIE[Wang et al., 2021] is a public dataset that consists of 1,494 images of Chinese examination paper head... SROIE[Huang et al., 2019] is a public dataset that contains 973 receipts in total. |
| Dataset Splits | No | Table 1 provides 'Training' and 'Testing' splits for the datasets (e.g., FUNSD: 149 Training, 50 Testing). However, it does not explicitly provide details for a separate 'validation' split. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used for running the experiments, such as CPU or GPU models. |
| Software Dependencies | No | The paper mentions using components like 'Adam optimizer' and 'Res Net-34' but does not specify software versions (e.g., Python, TensorFlow, PyTorch versions) needed for replication. |
| Experiment Setup | Yes | The model is trained from using the Adam optimizer with a learning rate of 0.0005... The γ is a focusing parameter intended to be 2. The α is used to balance the positive and negative classes and we set it to 0.75 in our experiments. ... λentity and λRe control the trade-off between losses, we set them to 1.0. ... if the matching probability is higher than a threshold (0.5)... we set the number of graph convolution layers to 2 and 8 heads for the multi-head attention. |