HABERTOR: An Efficient and Effective Deep Hatespeech Detector

by   Thanh Tran, et al.

We present our HABERTOR model for detecting hatespeech in large scale user-generated content. Inspired by the recent success of the BERT model, we propose several modifications to BERT to enhance the performance on the downstream hatespeech classification task. HABERTOR inherits BERT's architecture, but is different in four aspects: (i) it generates its own vocabularies and is pre-trained from the scratch using the largest scale hatespeech dataset; (ii) it consists of Quaternion-based factorized components, resulting in a much smaller number of parameters, faster training and inferencing, as well as less memory usage; (iii) it uses our proposed multi-source ensemble heads with a pooling layer for separate input sources, to further enhance its effectiveness; and (iv) it uses a regularized adversarial training with our proposed fine-grained and adaptive noise magnitude to enhance its robustness. Through experiments on the large-scale real-world hatespeech dataset with 1.4M annotated comments, we show that HABERTOR works better than 15 state-of-the-art hatespeech detection methods, including fine-tuning Language Models. In particular, comparing with BERT, our HABERTOR is 4 5 times faster in the training/inferencing phase, uses less than 1/3 of the memory, and has better performance, even though we pre-train it by using less than 1 the number of words. Our generalizability analysis shows that HABERTOR transfers well to other unseen hatespeech datasets and is a more efficient and effective alternative to BERT for the hatespeech classification.


AT-BERT: Adversarial Training BERT for Acronym Identification Winning Solution for SDU@AAAI-21

Acronym identification focuses on finding the acronyms and the phrases t...

RoChBert: Towards Robust BERT Fine-tuning for Chinese

Despite of the superb performance on a wide range of tasks, pre-trained ...

MAT: Mixed-Strategy Game of Adversarial Training in Fine-tuning

Fine-tuning large-scale pre-trained language models has been demonstrate...

Multi-CLS BERT: An Efficient Alternative to Traditional Ensembling

Ensembling BERT models often significantly improves accuracy, but at the...

RobBERTje: a Distilled Dutch BERT Model

Pre-trained large-scale language models such as BERT have gained a lot o...

Story Ending Prediction by Transferable BERT

Recent advances, such as GPT and BERT, have shown success in incorporati...

Optimizing small BERTs trained for German NER

Currently, the most widespread neural network architecture for training ...

Please sign up or login with your details

Forgot password? Click here to reset