Assessing the Impact of OCR Errors in Information Retrieval.
Guilherme Torresan BazzoGustavo Acauan LorentzDanny Suarez VargasViviane P. MoreiraPublished in: ECIR (2) (2020)
Keyphrases
- information retrieval
- recognition errors
- information retrieval systems
- optical character recognition
- post processing
- information extraction
- document collections
- preprocessing
- language model
- document processing
- query expansion
- information filtering
- data sets
- text retrieval
- error correction
- tf idf
- computational linguistics
- high impact
- error detection
- question answering
- language processing
- retrieval effectiveness
- relevance feedback
- knowledge discovery
- machine learning