Layout-Aware Information Extraction for Document-Grounded Dialogue: Dataset, Method and Demonstration.
Zhenyu ZhangBowen YuHaiyang YuTingwen LiuCheng FuJingyang LiChengguang TangJian SunYongbin LiPublished in: CoRR (2022)
Keyphrases
- high accuracy
- synthetic data
- information extraction
- significant improvement
- detection method
- dynamic programming
- computational complexity
- preprocessing
- neural network
- objective function
- pairwise
- information retrieval systems
- similarity measure
- data sets
- segmentation method
- document clustering
- precision and recall
- text categorization
- web documents
- document images
- document retrieval