Five Shades of Noise: Analyzing Machine Translation Errors in User-Generated Text.
Marlies van der WeesArianna BisazzaChristof MonzPublished in: NUT@IJCNLP (2015)
Keyphrases
- machine translation
- user generated
- natural language generation
- machine translation system
- word level
- language independent
- information extraction
- social media
- cross lingual
- multilingual documents
- natural language processing
- cross language information retrieval
- user generated content
- text mining
- target language
- web content
- text retrieval
- sentiment analysis
- user interests
- text documents
- statistical machine translation
- natural language
- sentence level
- information retrieval
- web documents
- source language
- knowledge base
- chinese english
- data mining
- keywords