Robust Layout-aware IE for Visually Rich Documents with Pre-trained Language Models.
Mengxi WeiYifan HeQiong ZhangPublished in: CoRR (2020)
Keyphrases
- language model
- document retrieval
- pre trained
- information retrieval
- ad hoc information retrieval
- document ranking
- vector space model
- query terms
- language modeling
- statistical language models
- document level
- retrieval model
- language modeling approaches
- n gram
- probabilistic model
- relevance model
- test collection
- passage retrieval
- query expansion
- term dependencies
- information retrieval systems
- relevant documents
- speech recognition
- document collections
- query specific
- language modeling framework
- smoothing methods
- training data
- retrieval effectiveness
- web documents
- supervised learning
- hidden markov models
- language models for information retrieval
- document clustering
- expert finding
- pseudo relevance feedback
- term frequency
- partial occlusion
- user queries
- information extraction
- keywords
- search engine