Generation of tunisian dialect corpora for adapting language models (Génération des corpus en dialecte tunisien pour la modélisation de langage d'un système de reconnaissance) [in French].
Rahma BoujelbanePublished in: RÉCITAL (2013)
Keyphrases
- language model
- statistical machine translation
- language modeling
- document level
- probabilistic model
- multiword
- n gram
- information retrieval
- document retrieval
- text corpora
- speech recognition
- test collection
- retrieval model
- query expansion
- translation model
- language modelling
- context sensitive
- hand crafted
- relevance model
- vector space model
- language models for information retrieval
- parallel corpus
- chinese english
- parallel corpora
- statistical language models
- smoothing methods
- machine translation system
- pseudo relevance feedback
- text data
- out of vocabulary
- query terms
- natural language processing
- document ranking
- text collections
- okapi bm
- ad hoc information retrieval
- spoken term detection