Construction of document feature vectors using BERT.
Hirotaka TanakaRui CaoJing BaiWen MaHiroyuki ShinnouPublished in: TAAI (2020)
Keyphrases
- feature vectors
- document collections
- document retrieval
- retrieval systems
- document images
- feature space
- information retrieval
- rotation invariant
- euclidean distance
- information retrieval systems
- keywords
- support vector machine
- similarity measure
- text documents
- feature extraction
- construction process
- gaussian mixture model
- web documents
- document clustering
- document representation
- document processing
- digital libraries
- data sets
- structured documents
- document content