Knowing Where and What: Unified Word Block Pretraining for Document Understanding. (arXiv:2207.13979v2 [cs.CL] UPDATED)

Due to the complex layouts of documents, it is challenging to extract
information for documents. Most previous studies develop multimodal pre-trained
models in a self-supervised way. In this paper, we focus on the embedding
learning of word blocks containing text and layout information, and propose
UTel, a language model with Unified TExt and Layout pre-training. Specifically,
we propose two pre-training tasks: Surrounding Word Prediction (SWP) for the
layout learning, and Contrastive learning of Word Embeddings (CWE) for
identifying different word …

arxiv document understanding understanding