Shall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive Study.
Boxin WangWei PingPeng XuLawrence McAfeeZihan LiuMohammad ShoeybiYi DongOleksii KuchaievBo LiChaowei XiaoAnima AnandkumarBryan CatanzaroPublished in: CoRR (2023)
Keyphrases
- language model
- autoregressive
- retrieval model
- document retrieval
- test collection
- query expansion
- language modeling
- information retrieval
- ad hoc information retrieval
- language models for information retrieval
- statistical language models
- query terms
- non stationary
- smoothing methods
- document length
- relevance model
- n gram
- probabilistic model
- gaussian markov random field
- document ranking
- random fields
- query specific
- retrieval effectiveness
- passage retrieval
- retrieval systems
- text retrieval
- term dependencies
- sar images
- speech recognition
- language modelling
- pseudo relevance feedback
- statistical language modeling
- ad hoc retrieval
- okapi bm
- vector space model
- information retrieval systems
- relevance feedback
- pairwise
- model selection
- search engine