EMBERT: A Pre-trained Language Model for Chinese Medical Text Mining.
Zerui CaiTaolin ZhangChengyu WangXiaofeng HePublished in: APWeb/WAIM (1) (2021)
Keyphrases
- language model
- pre trained
- text mining
- information retrieval
- language modeling
- n gram
- training data
- document retrieval
- word segmentation
- probabilistic model
- speech recognition
- information extraction
- training examples
- natural language processing
- query expansion
- retrieval model
- text documents
- text classification
- mixture model
- test collection
- document clustering
- smoothing methods
- control signals
- data mining
- data analysis
- knowledge discovery
- textual documents
- ad hoc information retrieval
- topic models
- cross lingual
- information retrieval systems
- visual tracking
- topic modeling
- translation model
- statistical machine translation
- natural language
- learning algorithm
- data sets