Domain-Specific Language Model Pre-Training for Korean Tax Law Classification.
Yeong Hyeon GuXianghua PiaoHelin YinDong JinRi ZhengSeong Joon YooPublished in: IEEE Access (2022)
Keyphrases
- language model
- domain specific
- language modeling
- n gram
- training set
- language modelling
- probabilistic model
- classification accuracy
- retrieval model
- document retrieval
- speech recognition
- query terms
- test collection
- text classification
- image classification
- query expansion
- supervised learning
- decision trees
- relevance model
- translation model
- statistical machine translation
- statistical language models
- information retrieval
- feature selection
- machine learning
- context sensitive
- pseudo relevance feedback
- smoothing methods
- search engine
- document length
- dirichlet prior
- ad hoc information retrieval
- language model for information retrieval
- mixture model
- vector space model
- feature vectors
- support vector
- document ranking
- query specific