Représentations continues dérivées des caractères pour un modèle de langue neuronal à vocabulaire ouvert (Opening the vocabulary of neural language models with character-level word representations).
Matthieu LabeauAlexandre AllauzenPublished in: TALN (2017)
Keyphrases
- language model
- n gram
- out of vocabulary
- word clouds
- spoken term detection
- language modeling
- document level
- translation model
- information retrieval
- document retrieval
- language modelling
- probabilistic model
- speech recognition
- query expansion
- retrieval model
- test collection
- multiword
- ad hoc information retrieval
- statistical language models
- statistical language modeling
- context sensitive
- spike trains
- word error rate
- language models for information retrieval
- document ranking
- broadcast news
- smoothing methods
- vector space model
- co occurrence
- keywords
- okapi bm
- language model for information retrieval
- word segmentation
- relevance model
- language independent
- query terms
- bayesian networks