- Typ
-
Werkzeug
- Autoren
-
Yarik Menchaca Resendiz, Roman Klinger
- Beschreibung
-
This repository contains code and data for the fine-tuning of T5 / Bart models to generate emotional event descriptions, as presented in the paper. There are three model configurations: condition on emotions (E), condition on emotions and appraisal (EA), and condition on appraisals (A).
- Referenz
-
Yarik Menchaca Resendiz and Roman Klinger. Affective natural language generation of event descriptions through fine-grained appraisal conditions. In Proceedings of the 16th International Conference on Natural Language Generation, Prague, Czech Republic, September 2023. Association for Computational Linguistics. accepted.
Citation:
@inproceedings{MenchacaResendiz2023,
title = {Affective Natural Language Generation of Event
Descriptions through Fine-grained Appraisal
Conditions},
author = {Menchaca Resendiz, Yarik and Klinger, Roman},
booktitle = {Proceedings of the 16th International Conference on
Natural Language Generation},
month = sep,
year = {2023},
address = {Prague, Czech Republic},
publisher = {Association for Computational Linguistics},
note = {accepted},
pdf = {https://www.romanklinger.de/publications/MenchacaResendiz_Klinger_INLG2023.pdf}
} - Download
![Dieses Bild zeigt Roman Klinger](https://www.ims.uni-stuttgart.de/documents/team/klingern/head-small.jpg?__scale=w:150,h:150,cx:69,cy:0,cw:425,ch:425)
Roman Klinger
Prof. Dr.Außerplanmäßiger Professor
![Dieses Bild zeigt Yarik Menchaca Resendiz](https://www.ims.uni-stuttgart.de/images/team/Yarik-Menchaca-resendiz.jpg?__scale=w:150,h:150,cx:0,cy:94,cw:2000,ch:2000)
Yarik Menchaca Resendiz
Doktorand