When and Why are Pre-trained Word Embeddings Useful for Neural Machine Translation?
Ye QiDevendra Singh SachanMatthieu FelixSarguna Janani PadmanabhanGraham NeubigPublished in: CoRR (2018)
Keyphrases
- machine translation
- pre trained
- word sense disambiguation
- statistical machine translation
- word level
- word alignment
- target language
- machine translation system
- parallel corpus
- cross lingual
- training data
- language independent
- cross language information retrieval
- statistical translation models
- source language
- bilingual dictionaries
- tasks in natural language processing
- training examples
- natural language processing
- information extraction
- translation model
- bilingual lexicon
- low dimensional
- natural language
- n gram
- neural network
- control signals
- chinese english
- information retrieval
- word order
- learning algorithm
- vector space
- data sets
- out of vocabulary
- small number
- multiword
- co occurrence