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 2409.16668cs.CL
收藏

面向反事实检测的主题感知因果干预

Topic-aware Causal Intervention for Counterfactual Detection

National University of Singapore(新加坡国立大学);Ho Chi Minh city University of Technology(胡志明市技术大学)

Thong Nguyen, Truc-My Nguyen

AI总结:

本文针对反事实检测中依赖线索短语和类别偏差问题,提出融合神经主题模型并进行因果干预的方法,在多个任务上取得最优性能。

摘要:

反事实语句描述的是未曾发生或不可能发生的事件,对众多自然语言处理应用具有重要价值。因此,我们研究反事实检测(CFD)问题,并致力于提升反事实检测模型的性能。以往模型依赖线索短语来预测反事实性,因此在测试阶段缺少线索短语提示时性能会显著下降。此外,这些模型倾向于将语句预测为非反事实而非反事实。为解决上述问题,我们提出将神经主题模型集成到反事实检测模型中,以捕获输入语句的全局语义。我们进一步对反事实检测模型的隐藏表示进行因果干预,以平衡类别标签的影响。大量实验表明,我们的方法在反事实检测任务以及其他对偏差敏感的任务上均优于先前最先进的反事实检测方法和偏差消除方法。

英文摘要:

Counterfactual statements, which describe events that did not or cannot take place, are beneficial to numerous NLP applications. Hence, we consider the problem of counterfactual detection (CFD) and seek to enhance the CFD models. Previous models are reliant on clue phrases to predict counterfactuality, so they suffer from significant performance drop when clue phrase hints do not exist during testing. Moreover, these models tend to predict non-counterfactuals over counterfactuals. To address these issues, we propose to integrate neural topic model into the CFD model to capture the global semantics of the input statement. We continue to causally intervene the hidden representations of the CFD model to balance the effect of the class labels. Extensive experiments show that our approach outperforms previous state-of-the-art CFD and bias-resolving methods in both the CFD and other bias-sensitive tasks.

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。

↑