SChuBERT: Scholarly Document Chunks with BERT-encoding boost Citation Count Prediction.
Thomas van DongenGideon Maillette de Buy WennigerLambert SchomakerPublished in: CoRR (2020)
Keyphrases
- prediction model
- scientific documents
- prediction accuracy
- scientific papers
- information retrieval
- digital libraries
- document classification
- document collections
- prediction algorithm
- information retrieval systems
- document images
- prediction error
- document clustering
- document retrieval
- database
- feature selection
- retrieval systems
- web documents
- text documents
- multimedia
- relevant documents
- semantic information
- document content
- digital documents
- intra coding
- language model