DocGraphLM
D
Docgraphlm
Overview :
DocGraphLM is a document graph language model for information extraction and question answering. It employs advanced vision-rich document understanding techniques, combining pre-trained language models and graph semantics. Its uniqueness lies in proposing a joint encoder architecture to represent documents and a novel link prediction method to reconstruct the document graph. DocGraphLM predicts the direction and distance between nodes through a convergent joint loss function, prioritizing neighborhood restoration and minimizing the weight of remote node detection. Experiments on three SotA datasets demonstrate that incorporating graph features consistently improves performance in information extraction and question-answering tasks. Furthermore, we report that employing graph features accelerates convergence during training, despite these features being constructed solely through link prediction.
Target Users :
DocGraphLM can handle information extraction and question-answering tasks in complex layout documents, suitable for scenarios requiring information extraction from structurally complex documents.
Total Visits: 29.7M
Top Region: US(17.94%)
Website Views : 49.4K
Use Cases
Apply DocGraphLM to medical documents to extract disease information and answer medical questions from medical literature.
Leverage DocGraphLM to analyze legal documents, extracting relevant information and answering legal questions from legal documents.
Use DocGraphLM in the financial sector to extract data from financial reports and answer related questions.
Features
Information Extraction
Question Answering
Document Understanding
Graph Feature Accelerated Training
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase