An approach to unsupervised historical text normalisation.
Petar MitankinStefan GerdjikovStoyan MihovPublished in: DATeCH (2014)
Keyphrases
- text retrieval
- information retrieval
- database
- semi supervised
- text information
- historical data
- historical documents
- text mining
- keywords
- data driven
- text segmentation
- supervised learning
- free text
- machine learning
- textual data
- text analysis
- weakly supervised
- document analysis
- syntactic categories
- document categorization
- historical manuscripts
- unsupervised manner
- text data
- retrieval model
- text documents
- neural network