Multilingual Training of Crosslingual Word Embeddings.
Long DuongHiroshi KanayamaTengfei MaSteven BirdTrevor CohnPublished in: EACL (1) (2017)
Keyphrases
- training set
- training corpus
- training process
- language specific
- artificial neural networks
- automatically generated
- digital libraries
- test set
- vector space
- training samples
- word sense disambiguation
- euclidean space
- cross lingual
- co occurrence
- supervised learning
- hilbert space
- parallel corpus
- data sets
- correlation clustering