Abstract
Biases continue to be prevalent in modern text and media, especially subjective bias – a special type of bias that introduces improper attitudes or presents a statement with the presupposition of truth. To tackle the problem of detecting and further mitigating subjective bias, we introduce a manually annotated parallel corpus WIKIBIAS with more than 4,000 sentence pairs from Wikipedia edits. This corpus contains annotations towards both sentence-level bias types and token-level biased segments. We present systematic analyses of our dataset and results achieved by a set of state-of-the-art baselines in terms of three tasks: bias classification, tagging biased segments, and neutralizing biased text. We find that current models still struggle with detecting multi-span biases despite their reasonable performances, suggesting that our dataset can serve as a useful research benchmark. We also demonstrate that models trained on our dataset can generalize well to multiple domains such as news and political speeches.- Anthology ID:
- 2021.findings-emnlp.155
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2021
- Month:
- November
- Year:
- 2021
- Address:
- Punta Cana, Dominican Republic
- Editors:
- Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
- Venue:
- Findings
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1799–1814
- Language:
- URL:
- https://aclanthology.org/2021.findings-emnlp.155
- DOI:
- 10.18653/v1/2021.findings-emnlp.155
- Cite (ACL):
- Yang Zhong, Jingfeng Yang, Wei Xu, and Diyi Yang. 2021. WIKIBIAS: Detecting Multi-Span Subjective Biases in Language. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 1799–1814, Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- WIKIBIAS: Detecting Multi-Span Subjective Biases in Language (Zhong et al., Findings 2021)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-3/2021.findings-emnlp.155.pdf
- Code
- cs329yangzhong/wikibias