Chinese Sequence Labeling with Semi-Supervised Boundary-Aware Language Model Pre-training.
Longhui ZhangDingkun LongMeishan ZhangYanzhao ZhangPengjun XieMin ZhangPublished in: LREC/COLING (2024)
Keyphrases
- language model
- sequence labeling
- semi supervised
- structured prediction
- named entity recognition
- language modeling
- conditional random fields
- probabilistic model
- supervised learning
- n gram
- document retrieval
- retrieval model
- information retrieval
- semi supervised learning
- query expansion
- dependency parsing
- test collection
- labeled and unlabeled data
- context sensitive
- training set
- mixture model
- graphical models
- unlabeled data
- pairwise
- relevance model
- labeled data
- translation model
- co training
- maximum margin
- generative model
- training data
- text classification
- prior knowledge
- latent variables
- active learning
- information extraction
- named entities
- natural language processing
- higher order