Unsupervised Word Segmentation Improves Dialectal Arabic to English Machine Translation.
Kamla Al-MannaiHassan SajjadAlaa KhaderFahad Al-ObaidliPreslav NakovStephan VogelPublished in: ANLP@EMNLP (2014)
Keyphrases
- machine translation
- word segmentation
- pos tagging
- cross lingual
- language independent
- handwriting recognition
- mt evaluation
- handwritten documents
- target language
- word level
- cross language information retrieval
- natural language processing
- information extraction
- language processing
- cross language
- word recognition
- brazilian portuguese
- chinese english
- source language
- statistical machine translation
- natural language
- word alignment
- parallel corpora
- n gram
- word sense disambiguation
- query translation
- parallel corpus
- out of vocabulary
- language modeling
- machine translation system
- semi supervised
- language specific
- text classification
- sentiment classification
- co occurrence
- document analysis
- bayesian networks
- part of speech
- grammar induction