Mapping Supervised Bilingual Word Embeddings from English to low-resource languages.
Sourav DuttaPublished in: CoRR (2019)
Keyphrases
- target language
- cross lingual
- statistical machine translation
- bilingual dictionaries
- sentence pairs
- source language
- machine translation
- parallel corpus
- language specific
- machine translation system
- indian languages
- query translation
- comparable corpora
- parallel corpora
- english chinese
- language independent
- word pairs
- word alignment
- cross language information retrieval
- word level
- english text
- translation model
- cross language
- cross lingual information retrieval
- bilingual lexicon
- chinese english
- character n grams
- multiword
- n gram
- word order
- language modeling
- out of vocabulary
- proper names
- sentence level
- machine readable dictionaries
- word sense
- cross language retrieval
- language resources
- linguistic resources
- language model
- semi supervised
- word forms
- word sense disambiguation
- language identification
- multilingual retrieval
- grammar induction
- monolingual retrieval
- spoken document retrieval
- word segmentation
- semantic relations
- document images
- compound words
- information retrieval
- statistical translation models
- news articles
- question answering
- text classification
- dimensionality reduction
- feature selection