Language classification from bilingual word embedding graphs.
Steffen EgerArmin HoenenPublished in: CoRR (2016)
Keyphrases
- parallel corpus
- support vector
- pattern recognition
- feature selection
- machine translation system
- word alignment
- target language
- machine learning
- image classification
- linguistic knowledge
- classification accuracy
- indian languages
- bilingual dictionaries
- co occurrence
- feature vectors
- training set
- feature space
- text classification
- feature extraction
- language resources
- lexical information
- english text
- bilingual lexicon
- source language
- graph embedding
- statistical machine translation
- multiword
- cross lingual
- graph matching
- machine translation
- feature set
- support vector machine