Linearization Weight Compression and In-Situ Hardware-Based Decompression for Attention-Based Neural Machine Translation.
Mijin GoJoonho KongArslan MunirPublished in: IEEE Access (2023)
Keyphrases
- machine translation
- compression ratio
- compression scheme
- data compression
- image compression
- compression algorithm
- cross lingual
- compressed data
- language independent
- language processing
- natural language processing
- information extraction
- natural language generation
- natural language
- word sense disambiguation
- machine translation system
- cross language information retrieval
- target language
- statistical machine translation
- chinese english
- word alignment
- language resources
- image quality
- parallel corpora
- word level
- tasks in natural language processing
- statistical translation models