Augmenting SMT with Generated Pseudo-parallel Corpora from Monolingual News Resources.
Krzysztof WolkAgnieszka WolkPublished in: WorldCIST (1) (2017)
Keyphrases
- parallel corpora
- statistical machine translation
- machine translation system
- machine translation
- cross lingual
- cross language information retrieval
- english chinese
- bilingual dictionaries
- parallel texts
- word alignment
- cross lingual information retrieval
- cross language
- query translation
- chinese english
- parallel corpus
- comparable corpora
- language independent
- translation model
- news articles
- source language
- linguistic resources
- target language
- text classification
- co occurrence
- natural language processing
- digital libraries
- text retrieval
- query expansion
- knn