P-SIF: Document Embeddings Using Partition Averaging.
Vivek GuptaAnkit SawPegah NokhizPraneeth NetrapalliPiyush RaiPartha P. TalukdarPublished in: CoRR (2020)
Keyphrases
- information retrieval
- document images
- document collections
- web documents
- document classification
- retrieval systems
- text documents
- dimensionality reduction
- document representation
- partitioning algorithm
- database
- vector space
- document clustering
- information retrieval systems
- distance measure
- image segmentation
- document content
- document analysis
- document structure
- relevant documents
- digital documents
- structured documents
- euclidean space
- semantic information
- feature extraction
- neural network