From Fully Trained to Fully Random Embeddings: Improving Neural Machine Translation with Compact Word Embedding Tables.
Krtin KumarPeyman PassbanMehdi RezagholizadehYiu Sing LauQun LiuPublished in: AAAI (2022)
Keyphrases
- machine translation
- word sense disambiguation
- statistical machine translation
- word level
- language independent
- machine translation system
- target language
- word alignment
- information extraction
- natural language
- cross language information retrieval
- vector space
- natural language generation
- parallel corpus
- cross lingual
- language processing
- grammar induction
- natural language processing
- source language
- bilingual dictionaries
- bilingual lexicon
- parallel corpora
- n gram
- probabilistic model