arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2312.09043cs.CL
收藏

情感分类中的主题偏差

Topic Bias in Emotion Classification

University of Stuttgart(斯图加特大学);University of Bamberg(班贝格大学)

Maximilian Wegge, Roman Klinger

AI总结:

该研究针对情感语料库因采样方式产生主题偏差、损害模型泛化性的问题,从数据与建模角度验证情感和特定主题的关联及对分类器的干扰,并证实梯度反转对抗校正的去偏方法可缓解该问题,呼吁构建更具代表性的语料资源。

摘要:

情感语料库通常基于关键词/话题标签搜索或通过要求研究参与者生成文本实例来采样。无论哪种情况,这些语料库都不是代表整个领域的均匀样本。我们假设,这种数据采集做法会导致语料库中占比过高的主题之间产生不切实际的相关性,从而损害模型的泛化能力。这种主题偏差可能会对诸如“我为姑姑的葬礼安排了仪式”这样的实例产生错误预测——因为葬礼事件在被标记为悲伤的实例中占比过高,尽管此处自豪的情绪更为合适。本文从数据和建模两个角度研究这种主题偏差。我们首先通过主题建模对一组情感语料库进行自动标注,并证明情感实际上与特定主题相关。此外,我们发现情感分类器会受到此类主题的混淆。最后,我们证明已有的通过梯度反转进行对抗校正的去偏差方法能够缓解这一问题。我们的工作指出了现有情感语料库存在的问题,即要公平评估从文本中预测情感概念的模型,需要更具代表性的资源。

英文摘要:

Emotion corpora are typically sampled based on keyword/hashtag search or by asking study participants to generate textual instances. In any case, these corpora are not uniform samples representing the entirety of a domain. We hypothesize that this practice of data acquisition leads to unrealistic correlations between overrepresented topics in these corpora that harm the generalizability of models. Such topic bias could lead to wrong predictions for instances like "I organized the service for my aunt's funeral." when funeral events are over-represented for instances labeled with sadness, despite the emotion of pride being more appropriate here. In this paper, we study this topic bias both from the data and the modeling perspective. We first label a set of emotion corpora automatically via topic modeling and show that emotions in fact correlate with specific topics. Further, we see that emotion classifiers are confounded by such topics. Finally, we show that the established debiasing method of adversarial correction via gradient reversal mitigates the issue. Our work points out issues with existing emotion corpora and that more representative resources are required for fair evaluation of models predicting affective concepts from text.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑