Comparing Rule-based and SMT-based Spelling Normalisation for English Historical Texts.
Gerold SchneiderEva PetterssonMichael PercillierPublished in: ListLang@NoDaLiDa (2017)
Keyphrases
- statistical machine translation
- brazilian portuguese
- training corpus
- natural language
- machine translation
- expert systems
- data driven
- english language
- language learning
- historical data
- native language
- linguistic analysis
- machine translation system
- phrase based smt
- english words
- rule based systems
- word alignment
- english text
- linguistic features
- spelling correction
- computing semantic relatedness
- answer questions
- translation model
- natural language generation
- natural language text
- cross language
- cross lingual
- text documents
- natural language processing
- information extraction