Logic Against Bias: Textual Entailment Mitigates Stereotypical Sentence Reasoning

17TH CONFERENCE OF THE EUROPEAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EACL 2023(2023)

引用 0|浏览30
暂无评分
摘要
Due to their similarity-based learning objectives, pretrained sentence encoders often internalize stereotypical assumptions that reflect the social biases that exist within their training corpora. In this paper, we describe several kinds of stereotypes concerning different communities that are present in popular sentence representation models, including pretrained next sentence prediction and contrastive sentence representation models. We compare such models to textual entailment models that learn language logic for a variety of downstream language understanding tasks. By comparing strong pretrained models based on text similarity with textual entailment learning, we conclude that the explicit logic learning with textual entailment can significantly reduce bias and improve the recognition of social communities, without an explicit de-biasing process. The code, model, and data associated with this work are publicly available at https: //github.com/luohongyin/ESP.git.
更多
查看译文
关键词
bias,textual,reasoning,sentence
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要