A Hybrid Approach to Align Sentences and Words in English-Hindi Parallel Corpora.
Niraj AswaniRobert J. GaizauskasPublished in: ParallelText@ACL (2005)
Keyphrases
- parallel corpora
- comparable corpora
- word pairs
- machine translation
- statistical machine translation
- parallel texts
- word alignment
- machine translation system
- source language
- target language
- english chinese
- out of vocabulary
- cross language information retrieval
- training corpus
- cross lingual
- parallel corpus
- bilingual dictionaries
- sentence level
- sentence pairs
- word sense disambiguation
- multiword
- query translation
- natural language
- semantic similarity
- language independent
- chinese english
- wikipedia articles
- translation model
- text corpora
- language modeling
- indian languages
- word level
- semantic relations
- language model
- labor intensive
- natural language processing
- semantic roles
- semantic relationships
- cross language
- topic models
- information extraction
- text mining
- novelty detection
- text classification
- n gram
- semantic network
- multi document summarization
- word segmentation