CRF-based bibliography extraction from reference strings using a small amount of training data.
Daiki NamikoshiManabu OhtaAtsuhiro TakasuJun AdachiPublished in: ICDIM (2017)
Keyphrases
- training data
- conditional random fields
- information extraction
- data sets
- decision trees
- pairwise
- small number
- markov random field
- prior knowledge
- graphical models
- supervised learning
- labeled data for training
- random fields
- test data
- input data
- classification accuracy
- support vector machine
- semi supervised learning
- training samples
- probabilistic model
- training set
- maximum entropy
- learning algorithm
- training dataset
- hamming distance
- alphabet size
- finite alphabet
- information retrieval