Abstract
This paper presents the DuluthNLP submission to Task 7 of the SemEval 2021 competition on Detecting and Rating Humor and Offense. In it, we explain the approach used to train the model together with the process of fine-tuning our model in getting the results. We focus on humor detection, rating, and of-fense rating, representing three out of the four subtasks that were provided. We show that optimizing hyper-parameters for learning rate, batch size and number of epochs can increase the accuracy and F1 score for humor detection- Anthology ID:
- 2021.semeval-1.169
- Volume:
- Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)
- Month:
- August
- Year:
- 2021
- Address:
- Online
- Editors:
- Alexis Palmer, Nathan Schneider, Natalie Schluter, Guy Emerson, Aurelie Herbelot, Xiaodan Zhu
- Venue:
- SemEval
- SIG:
- SIGLEX
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1196–1203
- Language:
- URL:
- https://aclanthology.org/2021.semeval-1.169
- DOI:
- 10.18653/v1/2021.semeval-1.169
- Cite (ACL):
- Samuel Akrah. 2021. DuluthNLP at SemEval-2021 Task 7: Fine-Tuning RoBERTa Model for Humor Detection and Offense Rating. In Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021), pages 1196–1203, Online. Association for Computational Linguistics.
- Cite (Informal):
- DuluthNLP at SemEval-2021 Task 7: Fine-Tuning RoBERTa Model for Humor Detection and Offense Rating (Akrah, SemEval 2021)
- PDF:
- https://preview.aclanthology.org/revert-3132-ingestion-checklist/2021.semeval-1.169.pdf
- Code
- akrahdan/semeval2021