Language Modeling Is Compression.
Grégoire DelétangAnian RuossPaul-Ambroise DuquenneElliot CattTim GeneweinChristopher MatternJordi Grau-MoyaLi Kevin WenliangMatthew AitchisonLaurent OrseauMarcus HutterJoel VenessPublished in: ICLR (2024)
Keyphrases
- language modeling
- language model
- information retrieval
- retrieval model
- query expansion
- probabilistic model
- n gram
- cross lingual
- text classification
- document length
- trec collections
- relevance model
- document retrieval
- comparable corpora
- machine translation
- sentence retrieval
- pseudo feedback
- improvements in retrieval effectiveness
- term weighting schemes
- text categorization
- text mining
- learning algorithm