SsciBERT: a pre-trained language model for social science texts.
Si ShenJiangfeng LiuLitao LinYing HuangLin ZhangChang LiuYutong FengDongbo WangPublished in: Scientometrics (2023)
Keyphrases
- language model
- social sciences
- pre trained
- language modeling
- training data
- computer science
- n gram
- probabilistic model
- training examples
- speech recognition
- retrieval model
- query expansion
- ad hoc information retrieval
- context sensitive
- mixture model
- control signals
- social scientists
- information retrieval
- data sets
- test collection
- supervised learning
- natural language
- expectation maximization
- small number
- translation model
- multimedia
- feature selection
- neural network