DocLLM: A layout-aware generative language model for multimodal document understanding.
Dongsheng WangNatraj RamanMathieu SibueZhiqiang MaPetr BabkinSimerjot KaurYulong PeiArmineh NourbakhshXiaomo LiuPublished in: CoRR (2024)
Keyphrases
- language model
- document understanding
- designing effective
- automatic summarization
- automatic text summarization
- document clustering
- language modeling
- multi document summarization
- probabilistic model
- generative model
- n gram
- document retrieval
- query expansion
- language modeling framework
- retrieval model
- information retrieval
- smoothing methods
- test collection
- translation model
- document representation
- vector space model
- document ranking
- graphical models
- k means