Unsupervised Boundary-Aware Language Model Pretraining for Chinese Sequence Labeling.
Peijie JiangDingkun LongYanzhao ZhangPengjun XieMeishan ZhangMin ZhangPublished in: CoRR (2022)
Keyphrases
- language model
- sequence labeling
- conditional random fields
- probabilistic model
- language modeling
- dependency parsing
- n gram
- word segmentation
- named entity recognition
- structured prediction
- document retrieval
- test collection
- information retrieval
- retrieval model
- query expansion
- unsupervised learning
- context sensitive
- higher order
- crf model
- information extraction
- relevance model
- supervised learning
- translation model
- machine learning
- generative model
- semi supervised
- maximum likelihood
- multiword