Improving MT System Using Extracted Parallel Fragments of Text from Comparable Corpora.
Rajdeep GuptaSantanu PalSivaji BandyopadhyayPublished in: BUCC@ACL (2013)
Keyphrases
- parallel corpora
- comparable corpora
- cross language information retrieval
- machine translation
- word pairs
- machine translation system
- sentence level
- cross lingual
- query translation
- text corpora
- language independent
- text mining
- text retrieval
- cross language
- bilingual lexicon
- labor intensive
- language modeling
- text documents
- linguistic resources
- bilingual dictionaries
- translation model
- semantic relations
- search engine
- source language
- natural language
- information extraction
- natural language processing
- target language
- sentiment analysis
- news articles
- fully automated
- wikipedia articles
- keywords
- domain dependent
- similarity measure
- information retrieval systems
- information retrieval
- machine learning