Human in the loop: How to effectively create coherent topics by manually labeling only a few documents per class.
Anton ThielmannChristoph WeisserBenjamin SäfkenPublished in: CoRR (2022)
Keyphrases
- information retrieval
- text documents
- keywords
- newspaper articles
- highly relevant
- information retrieval systems
- document set
- key concepts
- document retrieval
- document collections
- retrieval systems
- manually constructed
- manually generated
- text categorization
- related topics
- document clustering
- topic detection
- latent topics
- web documents
- class labels
- human subjects
- topic discovery
- document classification
- topic modeling
- wikipedia pages
- topic hierarchy
- user interests
- automatically generated
- vector space
- wordnet
- active learning
- xml documents
- image segmentation
- clustering algorithm
- metadata