Adaptive Ensemble Self-Distillation With Consistent Gradients for Fast Inference of Pretrained Language Models.
Jun KongJin WangXuejie ZhangPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2024)
Keyphrases
- language model
- language modeling
- speech recognition
- n gram
- probabilistic model
- document retrieval
- information retrieval
- statistical language models
- language modelling
- query expansion
- test collection
- retrieval model
- context sensitive
- smoothing methods
- vector space model
- translation model
- training set
- feature selection
- document ranking
- language models for information retrieval
- relevance model
- pseudo relevance feedback
- machine learning
- mixture model
- ad hoc information retrieval
- language model for information retrieval
- query specific
- speech signal
- cross lingual
- bayesian networks