Data Augmentation with Unsupervised Machine Translation Improves the Structural Similarity of Cross-lingual Word Embeddings.
Sosuke NishikawaRyokan RiYoshimasa TsuruokaPublished in: ACL (student) (2021)
Keyphrases
- machine translation
- cross lingual
- word alignment
- language independent
- parallel corpus
- data analysis
- structural similarity
- machine translation system
- cross language information retrieval
- word sense disambiguation
- statistical machine translation
- natural language
- information extraction
- language modeling
- parallel corpora
- natural language processing
- supervised learning
- target language
- word level
- language specific
- cross language
- structural information
- text mining
- data points
- translation model
- sentiment classification
- information retrieval
- document clustering
- dimensionality reduction
- cross lingual information retrieval