Flan-MoE: Scaling Instruction-Finetuned Language Models with Sparse Mixture of Experts.
Sheng ShenLe HouYanqi ZhouNan DuShayne LongpreJason WeiHyung Won ChungBarret ZophWilliam FedusXinyun ChenTu VuYuexin WuWuyang ChenAlbert WebsonYunxuan LiVincent ZhaoHongkun YuKurt KeutzerTrevor DarrellDenny ZhouPublished in: CoRR (2023)
Keyphrases
- language model
- mixture model
- language modeling
- n gram
- probabilistic model
- information retrieval
- language modelling
- expert finding
- query expansion
- test collection
- speech recognition
- context sensitive
- retrieval model
- ad hoc information retrieval
- document retrieval
- high dimensional
- language model for information retrieval
- smoothing methods
- expectation maximization
- vector space model
- machine learning
- statistical language models
- multimedia
- document length
- language models for information retrieval
- pseudo relevance feedback
- translation model
- word error rate
- okapi bm
- query terms
- document ranking
- retrieval effectiveness