Automated Text Simplification as a Preprocessing Step for Machine Translation into an Under-resourced Language.
Sanja StajnerMaja PopovicPublished in: RANLP (2019)
Keyphrases
- preprocessing step
- machine translation
- language specific
- machine translation system
- target language
- preprocessing
- source language
- language processing
- natural language generation
- multilingual documents
- language resources
- language independent
- natural language
- parallel corpus
- natural language processing
- word level
- statistical machine translation
- cross lingual
- feature selection
- parallel corpora
- word sense disambiguation
- computational linguistics
- feature extraction
- bilingual dictionaries
- information extraction
- word order
- word alignment
- cross language information retrieval
- dimensionality reduction
- text mining
- comparable corpora
- word pairs
- text retrieval
- chinese english
- data mining
- bilingual lexicon
- document retrieval
- knowledge discovery
- machine learning