Adapting Pretrained Representations for Text Mining.
Yu MengJiaxin HuangYu ZhangJiawei HanPublished in: KDD (2022)
Keyphrases
- text mining
- textual documents
- text documents
- natural language processing
- biomedical literature
- document clustering
- web mining
- text classification
- multiple representations
- information retrieval
- information extraction
- text categorisation
- high level
- named entities
- decision trees
- website
- latent dirichlet allocation
- text clustering
- data mining
- probability distribution
- bayesian networks
- topic models
- information systems
- textual data
- topic modeling
- machine learning
- real world
- neural network