An Assessment of the Impact of OCR Noise on Language Models.
Konstantin TodorovGiovanni ColavizzaPublished in: ICAART (2) (2022)
Keyphrases
- language model
- language modeling
- probabilistic model
- n gram
- retrieval model
- information retrieval
- speech recognition
- language modelling
- document retrieval
- query expansion
- test collection
- statistical language models
- document images
- smoothing methods
- ad hoc information retrieval
- query terms
- context sensitive
- document ranking
- optical character recognition
- language model for information retrieval
- relevance model
- character recognition
- pseudo relevance feedback
- hidden markov models
- web search
- document length
- image retrieval
- language models for information retrieval
- bayesian networks