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 2310.20697cs.CLstat.ME
收藏

Text-Transport:面向学习自然语言因果效应的方法

Text-Transport: Toward Learning Causal Effects of Natural Language

Carnegie Mellon University(卡内基梅隆大学)

Victoria Lin, Louis-Philippe Morency, Eli Ben-Michael

AI总结:

本文提出 Text-Transport 方法,利用分布偏移在文本领域间迁移因果效应估计,避免目标领域强假设,并通过社交媒体仇恨言论场景验证其必要性。

摘要:

随着语言技术在现实世界中的应用日益广泛,理解语言变化如何影响读者感知变得十分重要。这一问题可以形式化为:改变某个语言属性(如情感)对读者对文本反应所产生的因果效应。本文提出了 Text-Transport,一种在任意文本分布下从自然语言中估计因果效应的方法。当前有效的因果效应估计方法需要对数据做出强假设,这意味着能够用于估计有效因果效应的数据往往不能代表实际感兴趣的目标领域。为解决这一问题,我们利用分布偏移的概念来描述一种能够在领域之间迁移因果效应的估计器,从而避免在目标领域中依赖强假设。我们推导了该估计器不确定性的统计保证,并报告了实证结果和分析,支持 Text-Transport 在不同数据设置下的有效性。最后,我们使用 Text-Transport 研究了一个现实场景——社交媒体上的仇恨言论——在该场景中,因果效应在不同文本领域之间确实存在显著偏移,证明了在自然语言上进行因果推断时进行迁移的必要性。

英文摘要:

As language technologies gain prominence in real-world settings, it is important to understand how changes to language affect reader perceptions. This can be formalized as the causal effect of varying a linguistic attribute (e.g., sentiment) on a reader's response to the text. In this paper, we introduce Text-Transport, a method for estimation of causal effects from natural language under any text distribution. Current approaches for valid causal effect estimation require strong assumptions about the data, meaning the data from which one can estimate valid causal effects often is not representative of the actual target domain of interest. To address this issue, we leverage the notion of distribution shift to describe an estimator that transports causal effects between domains, bypassing the need for strong assumptions in the target domain. We derive statistical guarantees on the uncertainty of this estimator, and we report empirical results and analyses that support the validity of Text-Transport across data settings. Finally, we use Text-Transport to study a realistic setting--hate speech on social media--in which causal effects do shift significantly between text domains, demonstrating the necessity of transport when conducting causal inference on natural language.

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。

↑