Skip to content
conftrace_
2021 SemEval SemEval 2021

SRPOL DIALOGUE SYSTEMS at SemEval-2021 Task 5: Automatic Generation of Training Data for Toxic Spans Detection

Abstract

AbstractThis paper presents a system used for SemEval-2021 Task 5: Toxic Spans Detection. Our system is an ensemble of BERT-based models for binary word classification, trained on a dataset extended by toxic comments modified and generated by two language models. For the toxic word classification, the prediction threshold value was optimized separately for every comment, in order to maximize the expected F1 value.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing

Authors

Michał Satława, Katarzyna Zamłyńska, Jarosław Piersa, Joanna Kolis, Klaudia Firląg, Katarzyna Beksa, Zuzanna Bordzicka, Christian Goltz, Paweł Bujnowski, Piotr Andruszkiewicz

Topics

Artificial Intelligence > Core AI > Foundation Models Machine Learning > Learning Types > Self-Supervised Learning Machine Learning > Application Areas > Data Augmentation Machine Learning > Application Areas > Model Merging Natural Language Processing > Applications > Text Classification Natural Language Processing > Resources & Methods > Large Language Models

Keywords

binary classification ensemble learning data augmentation bert model language model ensemble model pre-trained language model threshold optimization toxic span detection toxic word classification training data generation transformer model binary word classification
Download PDF

More from SemEval 2021

All SemEval 2021 papers →
YoungSheldon at SemEval-2021 Task 5: Fine-tuning Pre-trained Language Models for Toxic Spans Detection using Token classification Objective
HLE-UPC at SemEval-2021 Task 5: Multi-Depth DistilBERT for Toxic Spans Detection
Lone Pine at SemEval-2021 Task 5: Fine-Grained Detection of Hate Speech Using BERToxic
SINAI at SemEval-2021 Task 5: Combining Embeddings in a BiLSTM-CRF model for Toxic Spans Detection
CSECU-DSG at SemEval-2021 Task 5: Leveraging Ensemble of Sequence Tagging Models for Toxic Spans Detection
UTNLP at SemEval-2021 Task 5: A Comparative Analysis of Toxic Span Detection using Attention-based, Named Entity Recognition, and Ensemble Models