Training Large-Vocabulary Neural Language Models by Private Federated Learning for Resource-Constrained Devices.
Mingbin XuCongzheng SongYe TianNeha AgrawalFilip GranqvistRogier C. van DalenXiao ZhangArturo ArguetaShiyi HanYaqiao DengLeo LiuAnmol WaliaAlex JinPublished in: CoRR (2022)
Keyphrases
- language model
- resource constrained
- probabilistic model
- speech recognition
- language modeling
- n gram
- information retrieval
- biologically plausible
- test collection
- smoothing methods
- document ranking
- translation model
- embedded systems
- document retrieval
- lightweight
- text classification
- low cost
- sensor networks
- active learning