Spell Checking Techniques for Replacement of Unknown Words and Data Cleaning for Haitian Creole SMS Translation.
Sara StymnePublished in: WMT@EMNLP (2011)
Keyphrases
- data cleaning
- unknown words
- data integration
- record linkage
- morphological analysis
- data quality
- outlier detection
- text classification
- word segmentation
- database
- missing values
- machine translation
- fraud detection
- data warehousing
- data processing
- web usage mining
- language processing
- word sense
- part of speech
- data warehouse
- machine learning
- previously unseen
- information retrieval
- data mining
- databases
- integrity constraints
- knowledge base
- n gram
- database systems
- natural language processing
- information extraction
- data model