Planting and Mitigating Memorized Content in Predictive-Text Language Models.
C. M. DowneyWei DaiHuseyin A. InanKim LaineSaurabh NaikTomasz ReligaPublished in: CoRR (2022)
Keyphrases
- language model
- information retrieval
- language modeling
- textual content
- document retrieval
- document level
- n gram
- probabilistic model
- query expansion
- retrieval model
- text retrieval
- test collection
- statistical language models
- language models for information retrieval
- language modelling
- web documents
- vector space model
- multimedia
- semantic information
- context sensitive
- multiword
- speech recognition
- smoothing methods
- query specific
- ad hoc information retrieval
- spoken term detection
- digital libraries
- translation model
- language model for information retrieval
- statistical language modeling
- improve retrieval effectiveness
- co occurrence
- text classification
- passage retrieval
- relevance model
- pseudo relevance feedback