LCP-dropout: Compression-based Multiple Subword Segmentation for Neural Machine Translation.
Keita NonakaKazutaka YamanouchiTomohiro ITsuyoshi OkitaKazutaka ShimadaHiroshi SakamotoPublished in: CoRR (2022)
Keyphrases
- machine translation
- natural language processing
- cross lingual
- language independent
- target language
- language processing
- image segmentation
- word sense disambiguation
- natural language generation
- word alignment
- cross language information retrieval
- chinese english
- information extraction
- natural language
- statistical machine translation
- tasks in natural language processing
- multilingual documents
- machine transliteration
- parallel corpus
- query translation
- word level
- source language
- information retrieval systems
- text mining
- statistical translation models
- artificial intelligence
- language resources
- knowledge base