Jiapeng Wang

Hi, since LiLT does not introduce image information yet, it cannot directly be used as an object detection model. However, maybe you can use it to assist the traditional visual...

Hi, in your config, it seems that you use `roberta-base` tokenizer with `lilt-infoxlm-base` model, which is inconsistent. You need to use the `xlm-roberta-base` tokenizer. And the `per_device_train_batch_size` equals to 1...

Hi, Maybe you can refer to [Test-Time Adaptation for Visual Document Understanding](https://arxiv.org/abs/2206.07240).

Hi, (1) Yes. You can write what you want to do under https://github.com/jpWang/LiLT/blob/main/examples/run_xfun_ser.py#L268. (2) I think you can go straight to create your own custom dataset.

Hi, @WenjinW @leitouran , Table 2 follows the fine-tune style of https://github.com/microsoft/unilm/blob/master/layoutlmft/examples/run_funsd.py, but Table 3 follows the fine-tune style of https://github.com/microsoft/unilm/blob/master/layoutlmft/examples/run_xfun_ser.py.

Hi, I think the main steps should be: - Organize your dataset into the format of FUNSD/XFUND, depending on your dataset is monolingual/multilingual. - Put `YourDataset.py` under `LiLTfinetune/data/datasets/`. You can...

Hi Manuel, thanks for your attention and recognition of our work. So far, we don't have an urgent plan to do it. However, if this work gets more attention, or...

@ManuelFay Hi Manuel, Recently I noticed that you have successfully made our LiLT models available on HuggingFace (For example, https://huggingface.co/manu/lilt-infoxlm-base). Thanks for your kind help and efforts ! 😃

> Hi folks (cc @jpWang), > > Happy to share that I've got a working HuggingFace implementation. I'm able to reproduce the results (F1 of 88% on FUNSD). The model...

> Hi @jpWang, > > I've opened a PR here to add LiLT to 🤗 Transformers: [huggingface/transformers#19450](https://github.com/huggingface/transformers/pull/19450). > > Would you like to create an organization for the company/research institute...