DocLLM: A Layout-Aware Generative Language Model for Multimodal Document Understanding.
Dongsheng WangNatraj RamanMathieu SibueZhiqiang MaPetr BabkinSimerjot KaurYulong PeiArmineh NourbakhshXiaomo LiuPublished in: ACL (1) (2024)
Keyphrases
- language model
- document understanding
- designing effective
- automatic summarization
- document clustering
- language modeling
- automatic text summarization
- probabilistic model
- generative model
- multi document summarization
- information retrieval
- document retrieval
- n gram
- retrieval model
- query expansion
- language modeling framework
- pseudo relevance feedback
- smoothing methods
- test collection
- vector space model
- retrieval effectiveness
- translation model
- text retrieval
- clustering method
- unsupervised learning
- information retrieval systems