Structure-Tags Improve Text Classification for Scholarly Document Quality Prediction.
Gideon Maillette de Buy WennigerThomas van DongenEleri AedmaaHerbert Teun KruitboschEdwin A. ValentijnLambert SchomakerPublished in: SDP@EMNLP (2020)
Keyphrases
- text classification
- quality prediction
- document classification
- text documents
- training corpus
- term frequency
- topic discovery
- text categorization
- web documents
- bag of words
- feature selection
- digital libraries
- document retrieval
- text mining
- semantic information
- text classifiers
- automatic text classification
- document structure
- neural network
- text data
- image quality
- image data
- keywords
- document collections
- part of speech
- information extraction
- logical structure
- metadata
- textual contents
- information retrieval