GLaM: Efficient Scaling of Language Models with Mixture-of-Experts.
Nan DuYanping HuangAndrew M. DaiSimon TongDmitry LepikhinYuanzhong XuMaxim KrikunYanqi ZhouAdams Wei YuOrhan FiratBarret ZophLiam FedusMaarten BosmaZongwei ZhouTao WangYu Emma WangKellie WebsterMarie PellatKevin RobinsonKathy Meier-HellsternToju DukeLucas DixonKun ZhangQuoc V. LeYonghui WuZhifeng ChenClaire CuiPublished in: CoRR (2021)
Keyphrases
- language model
- mixture model
- language modeling
- probabilistic model
- document retrieval
- n gram
- language modelling
- query expansion
- speech recognition
- test collection
- information retrieval
- document ranking
- retrieval model
- vector space model
- statistical language models
- language models for information retrieval
- ad hoc information retrieval
- generative model
- em algorithm
- query terms
- retrieval effectiveness
- expectation maximization
- pseudo relevance feedback
- translation model
- image retrieval
- smoothing methods
- machine learning