Skip to content

This project provides a flexible framework which can train domain-specific concept extractors on labeled data. It provides an easy way to do feature engineering and currently supports 24 different types of features.

Notifications You must be signed in to change notification settings

PAWSLabUniversityOfPittsburgh/Concept-Extraction

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

16 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Feature-based Concept Extraction

This project provides a flexible framework which can train domain-specific concept extractors on labeled data. It provides an easy way to do feature engineering and currently supports 24 different types of features.

Cite

If you use the code please cite the following paper:

Chau, H., Labutov, I., Thaker, K. et al. Automatic Concept Extraction for Domain and Student Modeling in Adaptive Textbooks. Int J Artif Intell Educ 31, 820–846 (2021). [Paper]

@article{Chau2020JAIED,
  author    = {Hung Chau and
               Igor Labutov and
               Khushboo Thaker and
               Daqing He and
               Peter Brusilovsky},
  title     = {Automatic Concept Extraction for Domain and Student Modeling in Adaptive Textbooks},
  journal   = {International Journal of Artificial Intelligence in Education},
  year      = {2020},
  publisher = {Springer}
}

If you use the dataset please cite the following paper:

Wang, M., Chau, H., Thaker, K. et al. Knowledge Annotation for Intelligent Textbooks. Tech Know Learn (2021). [Paper]

@article{wang2021knowledge,
  title={Knowledge Annotation for Intelligent Textbooks},
  author={Wang, Mengdi and Chau, Hung and Thaker, Khushboo and Brusilovsky, Peter and He, Daqing},
  journal={Technology, Knowledge and Learning},
  pages={1--22},
  year={2021},
  publisher={Springer}
}

About

This project provides a flexible framework which can train domain-specific concept extractors on labeled data. It provides an easy way to do feature engineering and currently supports 24 different types of features.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages