Quality Estimation and Translation Metrics via Pre-trained Word and Sentence Embeddings.
Elizaveta YankovskayaAndre TättarMark FishelPublished in: WMT (3) (2019)
Keyphrases
- quality estimation
- pre trained
- quality metrics
- parallel corpus
- source language
- target language
- word level
- sentence level
- machine translation
- statistical machine translation
- training data
- translation model
- machine translation system
- quality assessment
- image quality
- training examples
- dimensionality reduction
- human visual system
- data quality
- low dimensional
- control signals
- cross language information retrieval
- evaluation metrics
- language model
- probabilistic model
- data sets
- natural language processing
- small number
- active learning
- image sequences
- machine learning