MarkupLM, fine-tuned on WebSRC

Multimodal (text +markup language) pre-training for Document AI

Introduction

MarkupLM is a simple but effective multi-modal pre-training method of text and markup language for visually-rich document understanding and information extraction tasks, such as webpage QA and webpage information extraction. MarkupLM archives the SOTA results on multiple datasets. For more details, please refer to our paper: MarkupLM: Pre-training of Text and Markup Language for Visually-rich Document Understanding Junlong Li, Yiheng Xu, Lei Cui, Furu Wei

Usage

We refer to the docs and demo notebooks .

microsoft/markuplm-large-finetuned-websrc powered by Hugging Face Inference Toolkit

Send Request

You can use cURL or any REST Client to send a request to the AzureML endpoint with your AzureML token.

curl <AZUREML_ENDPOINT_URL> \
    -X POST \
    -H "Authorization: Bearer <AZUREML_TOKEN>" \
    -H "Content-Type: application/json" \
    -d '{"question": "What is my name?", "context": "My name is Clara and I live in Berkeley."}'

Supported Parameters

inputs (object): One (context, question) pair to answer
- context (string): The context to be used for answering the question
- question (string): The question to be answered
parameters (object):
- top_k (integer): The number of answers to return (will be chosen by order of likelihood). Note that we return less than topk answers if there are not enough options available within the context.
- doc_stride (integer): If the context is too long to fit with the question for the model, it will be split in several chunks with some overlap. This argument controls the size of that overlap.
- max_answer_len (integer): The maximum length of predicted answers (e.g., only answers with a shorter length are considered).
- max_seq_len (integer): The maximum length of the total sentence (context + question) in tokens of each chunk passed to the model. The context will be split in several chunks (using docStride as overlap) if needed.
- max_question_len (integer): The maximum length of the question after tokenization. It will be truncated if needed.
- handle_impossible_answer (boolean): Whether to accept impossible as an answer.
- align_to_words (boolean): Attempts to align the answer to real words. Improves quality on space separated languages. Might hurt on non-space-separated languages (like Japanese or Chinese)

Check the full API Specification at the Hugging Face Inference documentation .

Model Specifications

LicenseUnknown

Last UpdatedAugust 2025

ProviderHuggingFace

Quick Start