Accurate semantic textual similarity for cleaning noisy parallel corpora using semantic machine translation evaluation metric: The NRC supervised submissions to the Parallel Corpus Filtering task.
Chi-kiu LoMichel SimardDarlene A. StewartSamuel LarkinCyril GouttePatrick LittellPublished in: WMT (shared task) (2018)
Keyphrases
- machine translation
- parallel corpora
- parallel corpus
- natural language
- cross lingual
- cross language information retrieval
- machine translation system
- word pairs
- statistical machine translation
- semantic similarity
- language independent
- natural language processing
- target language
- query translation
- information extraction
- cross language
- semantic information
- evaluation metrics
- word alignment
- question answering
- source language
- supervised learning
- semantic features
- bilingual dictionaries
- translation model
- semantic space
- machine learning
- similarity measure