Word segmentation through cross-lingual word-to-phoneme alignment.
Felix StahlbergTim SchlippeStephan VogelTanja SchultzPublished in: SLT (2012)
Keyphrases
- word segmentation
- cross lingual
- word alignment
- word level
- language independent
- machine translation
- language modeling
- word recognition
- translation model
- cross language
- parallel corpus
- speech recognition
- language model
- text classification
- out of vocabulary
- sentiment classification
- news articles
- statistical machine translation
- machine translation system
- unknown words
- word sense
- transfer learning
- automatic speech recognition
- n gram
- language specific
- parallel corpora
- web pages
- source language
- query translation
- document clustering
- clustering method
- natural language processing
- information extraction
- high dimensional