MIDAS at SemEval-2019 Task 6: Identifying Offensive Posts and Targeted Offense from Twitter

Mahata, Debanjan; Zhang, Haimin; Uppal, Karan; Kumar, Yaman; Shah, Rajiv Ratn; Shahid, Simra; Mehnaz, Laiba; Anand, Sarthak

doi:10.18653/v1/s19-2122

Cited by 21 publications

(18 citation statements)

References 27 publications

(24 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some of the models that solved these tasks involve Convolutional Neural Networks (CNN) (Mahata et al, 2019), Long Short Term Memory Networks (LSTM) (Pham-Hong and Chokshi, 2020) or attention based models Wiedemann et al, 2020) branched from the BERT family (Devlin et al, 2019).…”

Section: Related Workmentioning

confidence: 99%

HLE-UPC at SemEval-2021 Task 5: Multi-Depth DistilBERT for Toxic Spans Detection

Palliser-Sans¹,

Rial-Farras²

2021

Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)

View full text Add to dashboard Cite

This paper presents our submission to SemEval-2021 Task 5: Toxic Spans Detection. The purpose of this task is to detect the spans that make a text toxic, which is a complex labour for several reasons. Firstly, because of the intrinsic subjectivity of toxicity, and secondly, due to toxicity not always coming from single words like insults or offends, but sometimes from whole expressions formed by words that may not be toxic individually. Following this idea of focusing on both single words and multi-word expressions, we study the impact of using a multi-depth DistilBERT model, which uses embeddings from different layers to estimate the final per-token toxicity. Our quantitative results show that using information from multiple depths boosts the performance of the model. Finally, we also analyze our best model qualitatively.

show abstract

Section: Related Workmentioning

confidence: 99%

HLE-UPC at SemEval-2021 Task 5: Multi-Depth DistilBERT for Toxic Spans Detection

Palliser-Sans¹,

Rial-Farras²

2021

Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)

View full text Add to dashboard Cite

show abstract

“…The participating teams used different approaches in their solutions. However, many teams used ensembles of deep learning models (Mahata et al, 2019) to benefit from its minimal need for features engineering and ability to boost the classifier performance. Moreover, to address the small dataset problem some teams used Bert model (Liu et al, 2019) and others utilized external datasets to further increase the training data (Seganti et al, 2019).…”

Section: Related Workmentioning

confidence: 99%

AlexU-BackTranslation-TL at SemEval-2020 Task 12: Improving Offensive Language Detection Using Data Augmentation and Transfer Learning

Ibrahim

Torki

El-Makky

2020

Proceedings of the Fourteenth Workshop on Semantic Evaluation

View full text Add to dashboard Cite

Social media platforms, online news commenting spaces, and many other public forums have become widely known for issues of abusive behavior such as cyber-bullying and personal attacks. In this paper, we use the annotated tweets of Offensive Language Identification Dataset (OLID) to train three levels of deep learning classifiers to solve the three sub-tasks associated with the dataset. Sub-task A is to determine if the tweet is toxic or not. Then, for offensive tweets, sub-task B requires determining whether the toxicity is targeted. Finally, for sub-task C, we predict the target of the offense; i.e. a group, individual or other entity. In our solution, we tackle the problem of class imbalance in the dataset by using back translation for data augmentation and utilizing fine-tuned BERT model in an ensemble of deep learning classifiers. We used this solution to participate in the three English sub-tasks of SemEval-2020 task 12. The proposed solution achieved 0.91393, 0.6300 and 0.57607 macro F1-average in sub-tasks A, B and C respectively. We achieved the 8th, 14th and 21st places for sub-tasks A, B and C respectively.

show abstract

“…A similar task was proposed in SemEval-2019 Task 6: Identifying and Categorizing Offensive Language in Social Media (OffensEval) (Zampieri et al, 2019). Most of the top-ranked teams in this task used transformer language models (Liu et al, 2019a;Zhu et al, 2019;Pelicon et al, 2019;Wu et al, 2019) or an ensemble of CNN and RNN (Mahata et al, 2019;Mitrović et al, 2019) to classify the sentences.…”

Section: Introductionmentioning

confidence: 99%

AStarTwice at SemEval-2021 Task 5: Toxic Span Detection Using RoBERTa-CRF, Domain Specific Pre-Training and Self-Training

T¹,

Jain²

2021

Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)

View full text Add to dashboard Cite

This paper describes our contribution to SemEval-2021 Task 5: Toxic Spans Detection. Our solution is built upon RoBERTa language model and Conditional Random Fields (CRF). We pre-trained RoBERTa on Civil Comments dataset, enabling it to create better contextual representation for this task. We also employed the semi-supervised learning technique of selftraining, which allowed us to extend our training dataset. In addition to these, we also identified some pre-processing steps that significantly improved our F1 score. Our proposed system achieved a rank of 41 with an F1 score of 66.16%.

show abstract

MIDAS at SemEval-2019 Task 6: Identifying Offensive Posts and Targeted Offense from Twitter

Cited by 21 publications

References 27 publications

HLE-UPC at SemEval-2021 Task 5: Multi-Depth DistilBERT for Toxic Spans Detection

HLE-UPC at SemEval-2021 Task 5: Multi-Depth DistilBERT for Toxic Spans Detection

AlexU-BackTranslation-TL at SemEval-2020 Task 12: Improving Offensive Language Detection Using Data Augmentation and Transfer Learning

AStarTwice at SemEval-2021 Task 5: Toxic Span Detection Using RoBERTa-CRF, Domain Specific Pre-Training and Self-Training

Contact Info

Product

Resources

About