NASH: A Simple Unified Framework of Structured Pruning for Accelerating Encoder-Decoder Language Models.
Jongwoo KoSeungjoon ParkYujin KimSumyeong AhnDu-Seong ChangEuijai AhnSe-Young YunPublished in: CoRR (2023)
Keyphrases
- language model
- unified framework
- probabilistic model
- language modeling
- speech recognition
- n gram
- language modelling
- query expansion
- document retrieval
- statistical language models
- low complexity
- information retrieval
- retrieval model
- context sensitive
- video codec
- motion estimation
- term dependencies
- distributed video coding
- decoding process
- error control
- translation model
- relevance model
- pseudo relevance feedback
- noisy channel
- wyner ziv video coding
- successive approximation
- vector space model
- smoothing methods
- hidden markov models
- computational complexity
- image segmentation