CINO: A Chinese Minority Pre-trained Language Model.
Ziqing YangZihang XuYiming CuiBaoxin WangMin LinDayong WuZhigang ChenPublished in: COLING (2022)
Keyphrases
- language model
- pre trained
- language modeling
- n gram
- training data
- probabilistic model
- document retrieval
- word segmentation
- information retrieval
- query expansion
- training examples
- retrieval model
- context sensitive
- speech recognition
- test collection
- control signals
- translation model
- smoothing methods
- ad hoc information retrieval
- relevance model
- mixture model
- markov random field
- information extraction
- pairwise
- training set
- face recognition