TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	REMOVE
Multi-label Condescension Detection	DPM	BERT-PCL	Macro-F1	43.28	# 2
Binary Condescension Detection	DPM	BERT-PCL	F1-score	63.69	# 1

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/pali-nlp-at-semeval-2022-task-4/binary-condescension-detection-on-dpm)](https://paperswithcode.com/sota/binary-condescension-detection-on-dpm?p=pali-nlp-at-semeval-2022-task-4)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/pali-nlp-at-semeval-2022-task-4/multi-label-condescension-detection-on-dpm)](https://paperswithcode.com/sota/multi-label-condescension-detection-on-dpm?p=pali-nlp-at-semeval-2022-task-4)`

PALI-NLP at SemEval-2022 Task 4: Discriminative Fine-tuning of Transformers for Patronizing and Condescending Language Detection

SemEval (NAACL) 2022 · Dou Hu, Mengyuan Zhou, Xiyang Du, Mengfei Yuan, Meizhi Jin, Lianxin Jiang, Yang Mo, Xiaofeng Shi ·

Patronizing and condescending language (PCL) has a large harmful impact and is difficult to detect, both for human judges and existing NLP systems. At SemEval-2022 Task 4, we propose a novel Transformer-based model and its ensembles to accurately understand such language context for PCL detection. To facilitate comprehension of the subtle and subjective nature of PCL, two fine-tuning strategies are applied to capture discriminative features from diverse linguistic behaviour and categorical distribution. The system achieves remarkable results on the official ranking, including 1st in Subtask 1 and 5th in Subtask 2. Extensive experiments on the task demonstrate the effectiveness of our system and its strategies.