Cross-Domain Classification of Moral Values - code

DOI:10.4121/8360d02b-b32f-4f07-bbf4-168915392bd9.v1
The DOI displayed above is for this specific version of this dataset, which is currently the latest. Newer versions may be published in the future. For a link that will always point to the latest version, please use
DOI: 10.4121/8360d02b-b32f-4f07-bbf4-168915392bd9
Datacite citation style:
Liscio, Enrico; Dondera, Alin E.; Geadau, Andrei; C.M. (Catholijn) Jonker; Murukannaiah, Pradeep K. (2023): Cross-Domain Classification of Moral Values - code. Version 1. 4TU.ResearchData. software. https://doi.org/10.4121/8360d02b-b32f-4f07-bbf4-168915392bd9.v1
Other citation styles (APA, Harvard, MLA, Vancouver, Chicago, IEEE) available at Datacite

Software

Code for the paper "Cross-Domain Classification of Moral Values", published at NAACL '22. This code implements a cross-domain evaluation of BERT, fastText, and LSTM across the seven datasets of MFTC. After being trained, the models are evaluated for generalizability, transferability, and catastrophic forgetting.

History

  • 2023-12-18 first online, published, posted

Publisher

4TU.ResearchData

Format

Python code

Associated peer-reviewed publication

Cross-Domain Classification of Moral Values

Funding

  • Hybrid Intelligence Center (a 10-year programme funded by the Dutch Ministry of Education, Culture and Science through the Netherlands Organisation for Scientific Research).

Organizations

TU Delft, Faculty of Electrical Engineering, Mathematics and Computer Science, Department of Intelligent Systems

DATA

To access the source code, use the following command:

git clone https://data.4tu.nl/v3/datasets/ae8d98d8-629f-4c61-bf05-8c15b5fb2ab0.git

Or download the latest commit as a ZIP.