When and Why Are Pre-Trained Word Embeddings Useful for Neural Machine Translation?
Ye QiDevendra Singh SachanMatthieu FelixSarguna PadmanabhanGraham NeubigPublished in: NAACL-HLT (2) (2018)
Keyphrases
- machine translation
- pre trained
- word sense disambiguation
- statistical machine translation
- word level
- word alignment
- target language
- machine translation system
- language independent
- training data
- source language
- information extraction
- natural language processing
- parallel corpus
- training examples
- cross lingual
- tasks in natural language processing
- statistical translation models
- grammar induction
- cross language information retrieval
- natural language
- neural network
- chinese english
- bilingual dictionaries
- control signals
- n gram
- low dimensional
- co occurrence
- bilingual lexicon
- word recognition
- information retrieval
- vector space
- translation model
- word segmentation
- parallel corpora
- wordnet
- supervised learning
- active learning
- word order