Hierarchical Transformers Are More Efficient Language Models.
Piotr NawrotSzymon TworkowskiMichal TyrolskiLukasz KaiserYuhuai WuChristian SzegedyHenryk MichalewskiPublished in: NAACL-HLT (Findings) (2022)
Keyphrases
- language model
- language modeling
- probabilistic model
- n gram
- document retrieval
- language modelling
- vector space model
- information retrieval
- speech recognition
- statistical language models
- test collection
- retrieval model
- ad hoc information retrieval
- query expansion
- pseudo relevance feedback
- relevance model
- document ranking
- cross lingual
- context sensitive
- retrieval effectiveness
- okapi bm