Low-resource speech translation of Urdu to English using semi-supervised part-of-speech tagging and transliteration.
A. Ryan AminzadehWade ShenPublished in: SLT (2008)
Keyphrases
- machine translation
- cross language information retrieval
- semi supervised
- cross language
- multi lingual
- natural language processing
- query translation
- machine transliteration
- language independent
- cross lingual
- named entity recognition
- bilingual dictionaries
- target language
- language identification
- web corpora
- pos tagging
- semi supervised learning
- language resources
- statistical machine translation
- parallel corpora
- english text
- cross language retrieval
- information access
- information extraction
- machine translation system
- speech recognition
- parallel corpus
- english chinese
- broadcast news
- natural language
- chinese english
- out of vocabulary
- comparable corpora
- word alignment
- word sense disambiguation
- noun phrases
- spoken language
- text retrieval
- supervised learning
- spoken document retrieval
- sentiment analysis
- text to speech
- translation model
- unlabeled data
- word level
- active learning
- dialogue system
- chinese word segmentation
- pairwise
- speaker identification
- speech signal
- part of speech
- question answering
- automatic speech recognition
- n gram
- named entities
- source language
- morphological analysis
- labeled data
- text input
- word segmentation
- information retrieval