Extracting Parallel Sentences from Comparable Corpora using Document Level Alignment.
Jason R. SmithChris QuirkKristina ToutanovaPublished in: HLT-NAACL (2010)
Keyphrases
- document level
- sentence level
- parallel corpora
- comparable corpora
- language model
- language modeling
- sentiment analysis
- sentiment classification
- multi document summarization
- query expansion
- cross language information retrieval
- novelty detection
- cross lingual
- document retrieval
- word alignment
- n gram
- news articles
- machine translation
- translation model
- information retrieval
- language independent
- query translation
- query processing