Corpus Augmentation by Sentence Segmentation for Low-Resource Neural Machine Translation.
Jinyi ZhangTadahiro MatsumotoPublished in: CoRR (2019)
Keyphrases
- machine translation
- parallel corpus
- statistical machine translation
- target language
- natural language
- training corpus
- machine translation system
- chinese english
- cross lingual
- parallel corpora
- word level
- natural language processing
- cross language information retrieval
- source language
- language independent
- word alignment
- word sense disambiguation
- sentence level
- pos tagging
- word segmentation
- language processing
- natural language generation
- linguistic features
- query translation
- part of speech
- information extraction
- semantic roles
- word pairs
- translation model
- language resources
- sentence retrieval
- brazilian portuguese
- text summarization
- co occurrence
- comparable corpora
- syntactic analysis
- sentiment analysis
- knowledge representation