Anchor-based Bilingual Word Embeddings for Low-Resource Languages.
Tobias EderViktor HangyaAlexander M. FraserPublished in: CoRR (2020)
Keyphrases
- statistical machine translation
- cross lingual
- bilingual dictionaries
- target language
- machine translation system
- sentence pairs
- machine translation
- indian languages
- source language
- parallel corpora
- word alignment
- word pairs
- parallel corpus
- query translation
- comparable corpora
- multiword
- language specific
- character n grams
- cross language information retrieval
- language independent
- translation model
- chinese english
- language resources
- expressive power
- word level
- word order
- n gram
- english chinese
- word segmentation
- bilingual lexicon
- cross lingual information retrieval
- natural language processing
- language modeling
- english text
- cross language
- word recognition
- word sense disambiguation
- machine readable dictionaries
- keywords
- resource allocation
- grammar induction
- text classification
- low dimensional
- statistical translation models
- co occurrence
- lexical knowledge
- text categorization
- document images
- semantic relations
- manifold learning
- linguistic resources