BERT large fine-tuned on MP-DocVQA

This is BERT trained on SinglePage DocVQA and fine-tuned on Multipage DocVQA (MP-DocVQA) dataset.

This model was used as a baseline in Hierarchical multimodal transformers for Multi-Page DocVQA.

• Training hyperparameters can be found in Table 8 of Appendix D.

How to use

Inference

How to use this model to perform inference on a sample question and context in PyTorch:

from transformers import AutoModelForQuestionAnswering, AutoTokenizer

model = AutoModelForQuestionAnswering.from_pretrained("rubentito/bert-large-mpdocvqa")
tokenizer = AutoTokenizer.from_pretrained("rubentito/bert-large-mpdocvqa")

question = "Replace me by any text you'd like."
context = "Put some context for answering"

encoded_input = tokenizer(question, context, return_tensors='pt')
output = model(**encoded_input)

start_pos = torch.argmax(output.start_logits, dim=-1).item()
end_pos = torch.argmax(output.end_logits.argmax, dim=-1).item()

pred_answer = context[start_pos:end_pos]

Metrics

Average Normalized Levenshtein Similarity (ANLS)

The standard metric for text-based VQA tasks (ST-VQA and DocVQA). It evaluates the method's reasoning capabilities while smoothly penalizes OCR recognition errors. Check Scene Text Visual Question Answering for detailed information.

Answer Page Prediction Accuracy (APPA)

In the MP-DocVQA task, the models can provide the index of the page where the information required to answer the question is located. For this subtask accuracy is used to evaluate the predictions: i.e. if the predicted page is correct or not. Check Hierarchical multimodal transformers for Multi-Page DocVQA for detailed information.

Model results

Extended experimentation can be found in Table 2 of Hierarchical multimodal transformers for Multi-Page DocVQA. You can also check the live leaderboard at the RRC Portal.

Citation Information

@article{tito2022hierarchical,
  title={Hierarchical multimodal transformers for Multi-Page DocVQA},
  author={Tito, Rub{\`e}n and Karatzas, Dimosthenis and Valveny, Ernest},
  journal={arXiv preprint arXiv:2212.05935},
  year={2022}
}