A paper accepted at AAAI 2021
2 December 2020, by Seid Muhie Yimam
The "Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI2021)" accepted the following paper:
- Binny Mathew ( IIT Kharagpur), Punyajoy Saha ( IIT Kharagpur), Seid Muhie Yimam ( Universität Hamburg), Chris Biemann (Universität Hamburg), Pawan Goyal ( IIT Kharagpur) and Animesh Mukherjee ( IIT Kharagpur), "HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection"
Abstract
Hate speech is a challenging issue plaguing the online social media. While better models for hate speech detection are continuously being developed, there is little research on the bias and interpretability aspects of hate speech. In this paper, we introduce HateXplain, the first benchmark hate speech dataset covering multiple aspects of the issue. Each post in our dataset is annotated from three different perspectives: the basic 3-class classification (i.e., hate, offensive or normal), the target community (i.e., the community that has been the victim of hate speech/offensive speech in the post), and the rationales, i.e., the portions of the post on which their labelling decision (as hate, offensive or normal) is based. We utilize existing state-of-the-art models and observe that even models that perform very well in classification, do not score high on explainability metrics like model plausibility and faithfulness. We also observe that models, which utilize the human rationales for training, perform better in reducing unintended bias towards target communities. Upon acceptance, we shall put our code and dataset in the public domain.