Generating Translation Corpora in Indic Languages: Cultivating Bilingual Texts for Cross Lingual Fertilization.
Niladri Sekhar DashArulmozi SelvrajMazhar HussainPublished in: ICON (2015)
Keyphrases
- cross lingual
- parallel corpus
- parallel corpora
- machine translation
- comparable corpora
- statistical machine translation
- chinese english
- cross lingual information retrieval
- language independent
- word sense
- translation model
- cross language
- linguistic resources
- sentence pairs
- query translation
- machine translation system
- word alignment
- natural language processing
- language modeling
- multi lingual
- european languages
- natural language
- text classification
- machine readable dictionaries
- bilingual dictionaries
- cross language information retrieval
- source language
- out of vocabulary
- mono lingual
- information extraction
- target language
- document clustering
- language specific
- cross language retrieval
- word segmentation
- news articles
- transfer learning
- indian languages
- word sense disambiguation
- machine learning
- text documents
- text retrieval
- language model
- knn
- text summarization