Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE.
Qihuang ZhongLiang DingYibing ZhanYu QiaoYonggang WenLi ShenJuhua LiuBaosheng YuBo DuYixin ChenXinbo GaoChunyan MiaoXiaoou TangDacheng TaoPublished in: CoRR (2022)
Keyphrases
- language model
- language modeling
- n gram
- document retrieval
- speech recognition
- probabilistic model
- information retrieval
- mixture model
- retrieval model
- context sensitive
- query expansion
- translation model
- smoothing methods
- statistical language models
- language modelling
- relevance model
- document ranking
- document length
- language models for information retrieval
- vector space model
- query terms
- test collection
- maximum likelihood