Using Communities of Words Derived from Multilingual Word Vectors for Cross-Language Information Retrieval in Indian Languages.
Paheli BhattacharyaPawan GoyalSudeshna SarkarPublished in: ACM Trans. Asian Low Resour. Lang. Inf. Process. (2019)
Keyphrases
- indian languages
- cross language information retrieval
- cross lingual
- translation model
- parallel corpus
- cross language
- out of vocabulary
- machine translation
- cross lingual information retrieval
- query translation
- word segmentation
- bilingual dictionaries
- english chinese
- chinese english
- parallel corpora
- comparable corpora
- character n grams
- language specific
- language identification
- language independent
- language modeling
- document images
- word sense
- linguistic resources
- n gram
- text classification
- word alignment
- statistical machine translation
- word sense disambiguation
- word level
- source language
- information extraction
- natural language processing
- information retrieval systems
- feature vectors
- target language
- news articles
- machine translation system
- multiword
- text categorization
- vector space