基于反事实表征的文本分类器解释方法
Explaining Text Classifiers with Counterfactual Representations
AI总结：
针对文本反事实构建中属性值难匹配真实事件的问题，提出在文本表征空间干预生成反事实的方法，符合Pearl因果框架，经实验验证有效，可用于分类器解释与偏差缓解。
摘要：
一种具备充分理论依据的分类器解释方法利用了反事实——即除了某一特征外，其他所有方面都与真实观测完全一致的假设事件。然而，由于部分属性值未必能与合理的真实事件相匹配，因此为文本构建此类反事实面临着特殊挑战。本文提出了一种通过在文本表征空间中进行干预来生成反事实的简单方法，可规避这一局限。我们认为本文的干预方式扰动最小，且在理论上是可靠的——它们与Pearl因果推断框架中定义的反事实相一致。为验证该方法，我们首先在合成数据集上开展实验，随后在真实反事实数据集上进行实验。这使得我们能够直接对比两类分类器预测结果：一类基于通过显式文本干预得到的真实反事实，另一类基于通过表征空间干预得到的本文方法生成的反事实。最后，我们研究了一个真实场景，其中本文的反事实既可用于解释分类器，也可用于偏差缓解。
英文摘要：
One well motivated explanation method for classifiers leverages counterfactuals which are hypothetical events identical to real observations in all aspects except for one feature. Constructing such counterfactual poses specific challenges for texts, however, as some attribute values may not necessarily align with plausible real-world events. In this paper we propose a simple method for generating counterfactuals by intervening in the space of text representations which bypasses this limitation. We argue that our interventions are minimally disruptive and that they are theoretically sound as they align with counterfactuals as defined in Pearl's causal inference framework. To validate our method, we conducted experiments first on a synthetic dataset and then on a realistic dataset of counterfactuals. This allows for a direct comparison between classifier predictions based on ground truth counterfactuals - obtained through explicit text interventions - and our counterfactuals, derived through interventions in the representation space. Eventually, we study a real world scenario where our counterfactuals can be leveraged both for explaining a classifier and for bias mitigation.
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。
