[Question]: Document-Parser for Ernie-Layout

PaddlePaddle / PaddleNLP

👑 Easy-to-use and powerful NLP and LLM library with 🤗 Awesome model zoo, supporting wide-range of NLP tasks from research to industrial applications, including 🗂Text Classification, 🔍 Neural Search, ❓ Question Answering, ℹ️ Information Extraction, 📄 Document Intelligence, 💌 Sentiment Analysis etc.

https://paddlenlp.readthedocs.io

Apache License 2.0

12.17k stars 2.94k forks source link

[Question]: Document-Parser for Ernie-Layout #6350

Open Mohamed-Dhouib opened 1 year ago

Mohamed-Dhouib commented 1 year ago

Hello, I noticed on the Ernie Layout Paper that you utilize Document-Parser for optimal organization of input text. However, I am unable to locate where this preprocessing occurs in the code. Could you kindly guide me to the relevant section or provide a link to the Document-Parser toolkit ? Thanks !

aashishpokharel commented 1 year ago

Have you found the preprocessing step @Mohamed-Dhouib ? I'm stuck in the same problem

Mohamed-Dhouib commented 1 year ago

@aashishpokharel unfortunately no ..

aashishpokharel commented 1 year ago

Just found the reason for that. #4015 mentions that the Serialization module hasn't been open sourced yet.