Amsqr at SemEval-2022 Task 4: Towards AutoNLP via Meta-Learning and Adversarial Data Augmentation for PCL Detection

Alejandro Mosquera


Abstract
This paper describes the use of AutoNLP techniques applied to the detection of patronizing and condescending language (PCL) in a binary classification scenario. The proposed approach combines meta-learning, in order to identify the best performing combination of deep learning architectures, with the synthesis of adversarial training examples; thus boosting robustness and model generalization. A submission from this system was evaluated as part of the first sub-task of SemEval 2022 - Task 4 and achieved an F1 score of 0.57%, which is 16 percentage points higher than the RoBERTa baseline provided by the organizers.
Anthology ID:
2022.semeval-1.66
Volume:
Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)
Month:
July
Year:
2022
Address:
Seattle, United States
Venue:
SemEval
SIGs:
SIGLEX | SIGSEM
Publisher:
Association for Computational Linguistics
Note:
Pages:
485–489
Language:
URL:
https://aclanthology.org/2022.semeval-1.66
DOI:
10.18653/v1/2022.semeval-1.66
Bibkey:
Cite (ACL):
Alejandro Mosquera. 2022. Amsqr at SemEval-2022 Task 4: Towards AutoNLP via Meta-Learning and Adversarial Data Augmentation for PCL Detection. In Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), pages 485–489, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Amsqr at SemEval-2022 Task 4: Towards AutoNLP via Meta-Learning and Adversarial Data Augmentation for PCL Detection (Mosquera, SemEval 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/auto-file-uploads/2022.semeval-1.66.pdf
Data
DPM