Estimating Contamination via Perplexity: Quantifying Memorisation in Language Model Evaluation.
Yucheng LiPublished in: CoRR (2023)
Keyphrases
- language model
- language modeling
- n gram
- document retrieval
- probabilistic model
- query expansion
- speech recognition
- language modelling
- mixture model
- test collection
- retrieval model
- information retrieval
- context sensitive
- vector space model
- multiword
- word error rate
- pseudo relevance feedback
- relevance model
- translation model
- statistical machine translation
- document ranking
- query specific
- language model for information retrieval
- error rate
- xml retrieval
- web search
- document length
- pseudo feedback
- ad hoc information retrieval