Evaluating and mitigating the impact of OCR errors on information retrieval.
Lucas Lima de OliveiraDanny Suarez VargasAntônio Marcelo Azevedo AlexandreFábio Corrêa CordeiroDiogo da Silva Magalhães GomesMax de Castro RodriguesRegis Kruel RomeuViviane Pereira MoreiraPublished in: Int. J. Digit. Libr. (2023)
Keyphrases
- information retrieval
- recognition errors
- information retrieval systems
- optical character recognition
- search engine
- document processing
- learning to rank
- post processing
- document collections
- retrieval effectiveness
- document images
- document retrieval
- information access
- test collection
- language model
- knowledge discovery
- retrieval systems
- neural network
- question answering
- query expansion
- risk management
- error correction
- text processing
- machine learning
- digital libraries
- document analysis
- language processing
- error analysis
- prediction error
- information seeking
- character recognition