XDoc: Unified Pre-training for Cross-Format Document Understanding.

Jingye Chen Tengchao Lv Lei Cui Cha Zhang Furu Wei

Published in: EMNLP (Findings) (2022)

Keyphrases

document understanding
designing effective
automatic summarization
automatic text summarization
multi document summarization
document clustering
training set
supervised learning
domain specific
artificial intelligence
metadata
machine learning
multimedia
image retrieval