Phonetic Normalization for Machine Translation of User Generated Content.
José Carlos Rosales NúñezDjamé SeddahGuillaume WisniewskiPublished in: W-NUT@EMNLP (2019)
Keyphrases
- user generated content
- machine translation
- word level
- social media
- language independent
- cross lingual
- information extraction
- natural language processing
- target language
- word sense disambiguation
- language processing
- cross language information retrieval
- speech recognition
- recommender systems
- natural language generation
- chinese english
- natural language
- machine translation system
- statistical machine translation
- parallel corpora
- word alignment
- language resources
- brazilian portuguese
- artificial intelligence
- multilingual documents