CSS-LM: A Contrastive Framework for Semi-supervised Fine-tuning of Pre-trained Language Models.
YuSheng SuXu HanYankai LinZhengyan ZhangZhiyuan LiuPeng LiMaosong SunPublished in: CoRR (2021)
Keyphrases
- language model
- fine tuning
- language modeling
- probabilistic model
- semi supervised
- document retrieval
- information retrieval
- n gram
- speech recognition
- query expansion
- pre trained
- retrieval model
- statistical language models
- language modelling
- vector space model
- pseudo relevance feedback
- relevance model
- document ranking
- test collection
- language models for information retrieval
- semi supervised learning
- machine learning
- labeled data
- unlabeled data