Text Sanitization Beyond Specific Domains: Zero-Shot Redaction & Substitution with Large Language Models.
Federico AlbaneseDaniel CiolekNicolás D'IppolitoPublished in: CoRR (2023)
Keyphrases
- language model
- specific domains
- information retrieval
- language modeling
- document level
- n gram
- document retrieval
- speech recognition
- domain specific
- retrieval model
- probabilistic model
- test collection
- language modelling
- text mining
- multiword
- query expansion
- statistical language models
- ad hoc information retrieval
- language model for information retrieval
- text retrieval
- keywords
- vector space model
- smoothing methods
- query terms
- relevance model
- information extraction
- translation model
- passage retrieval
- language models for information retrieval
- information retrieval systems
- text documents
- bag of words
- improve retrieval effectiveness
- statistical language modeling
- bayesian networks