Predicting Machine Translation Adequacy with Document Embeddings.
Mihaela VelaLiling TanPublished in: WMT@EMNLP (2015)
Keyphrases
- machine translation
- multilingual documents
- word level
- source language
- language independent
- information extraction
- target language
- cross lingual
- natural language processing
- cross language information retrieval
- language processing
- statistical machine translation
- word sense disambiguation
- word alignment
- document images
- information retrieval
- web documents
- chinese english
- natural language generation
- document classification
- language resources
- multilingual information retrieval
- vector space
- document collections
- document retrieval
- retrieval systems
- document clustering
- document representation
- information retrieval systems
- syntactic analysis
- parallel corpus
- text classification
- natural language
- document analysis
- text summarization
- tf idf
- machine learning
- text documents
- user queries