Using Transfer-based Language Models to Detect Hateful and Offensive Language Online

Isaksen, Vebjørn; Gambäck, Björn

doi:10.18653/v1/2020.alw-1.3

Cited by 22 publications

(11 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While BERT has been pre-trained using vast amounts of textual data, namely, all of Wikipedia and Google Books, the word encodings produced by BERT can benefit from further adaptation to the target domain (Gururangan et al, 2020). In a recent work, Isaksen and Gambäck (2020) applied BERT to the task of hate detection. They report results of finetuning and evaluating the base and large variants of BERT (BERT-base and BERT-large) on each of the DV and FN datasets.…”

Section: Hate Speech Detection With Pre-trained Language Modelsmentioning

confidence: 99%

Character-level HyperNetworks for Hate Speech Detection

Wullach,

Adler,

Minkov

2021

Preprint

View full text Add to dashboard Cite

The massive spread of hate speech, hateful content targeted at specific subpopulations, is a problem of critical social importance. Automated methods for hate speech detection typically employ state-of-the-art deep learning (DL)-based text classifiers-very large pre-trained neural language models of over 100 million parameters, adapting these models to the task of hate speech detection using relevant labeled datasets. Unfortunately, there are only numerous labeled datasets of limited size that are available for this purpose. We make several contributions with high potential for advancing this state of affairs. We present HyperNetworks for hate speech detection, a special class of DL networks whose weights are regulated by a small-scale auxiliary network. These architectures operate at character-level, as opposed to word-level, and are several magnitudes of order smaller compared to the popular DL classifiers. We further show that training hate detection classifiers using large amounts of automatically generated examples in a procedure named as data augmentation is beneficial in general, yet this practice especially boosts the performance of the proposed HyperNetworks. In fact, we achieve performance that is comparable or better than state-of-the-art language models, which are pre-trained and orders of magnitude larger, using this approach, as evaluated using five public hate speech datasets.

show abstract

Section: Hate Speech Detection With Pre-trained Language Modelsmentioning

confidence: 99%

Character-level HyperNetworks for Hate Speech Detection

Wullach,

Adler,

Minkov

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Besides, SOTA approaches like deep learning (Badjatiya et al, 2017) and transformers models (Isaksen and Gambäck, 2020) are applied in the hate speech detection and toxic posts classification. However, these models only classify based on the whole posts or documents.…”

Section: Related Workmentioning

confidence: 99%

UIT-ISE-NLP at SemEval-2021 Task 5: Toxic Spans Detection with BiLSTM-CRF and ToxicBERT Comment Classification

Luu¹,

Nguyen²

2021

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

View full text Add to dashboard Cite

show abstract

“…However, the authors did not mention the annotation process and the method for evaluating the quality of the dataset. Besides, on the hate speech detection problem, many state-of-the-art models give optimistic results such as deep learning models [4] and transformer language models [20]. Those models require largescale annotated datasets, which is a challenge for low-resource languages like Vietnamese.…”

Section: Related Workmentioning

confidence: 99%

A Large-scale Dataset for Hate Speech Detection on Vietnamese Social Media Texts

Luu,

Van Nguyen,

Nguyen

2021

Preprint

View full text Add to dashboard Cite

In recent years, Vietnam witnesses the mass development of social network users on different social platforms such as Facebook, Youtube, Instagram, and Tiktok. On social media, hate speech has become a critical problem for social network users. To solve this problem, we introduce the ViHSD -a human-annotated dataset for automatically detecting hate speech on the social network. This dataset contains over 30,000 comments, each comment in the dataset has one of three labels: CLEAN, OFFENSIVE, or HATE. Besides, we introduce the data creation process for annotating and evaluating the quality of the dataset. Finally, we evaluate the dataset by deep learning and transformer models.

show abstract

Using Transfer-based Language Models to Detect Hateful and Offensive Language Online

Cited by 22 publications

References 37 publications

Character-level HyperNetworks for Hate Speech Detection

Character-level HyperNetworks for Hate Speech Detection

UIT-ISE-NLP at SemEval-2021 Task 5: Toxic Spans Detection with BiLSTM-CRF and ToxicBERT Comment Classification

A Large-scale Dataset for Hate Speech Detection on Vietnamese Social Media Texts

Contact Info

Product

Resources

About