no code implementations • 6 Apr 2024 • Tosin Adewumi, Nudrat Habib, Lama Alkhaled, Elisa Barney
We then randomly sampled 162 chunks for human evaluation from each of the annotated books, based on the error margin of 7% and a confidence level of 95% for the book with the most chunks (Great Expectations by Charles Dickens, having 922 chunks).
1 code implementation • 1 Feb 2024 • Tosin Adewumi, Nudrat Habib, Lama Alkhaled, Elisa Barney
We introduce Instruction Document Visual Question Answering (iDocVQA) dataset and Large Language Document (LLaDoc) model, for training Language-Vision (LV) models for document analysis and predictions on document images, respectively.