arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.01969cs.CL
收藏

使用图神经网络生成最优且高效的文本反事实样本

Optimal and efficient text counterfactuals using Graph Neural Networks

Artificial Intelligence and Learning Systems Laboratory(人工智能与学习系统实验室);School of Electrical and Computer Engineering(电气与计算机工程学院);National Technical University of Athens(雅典技术大学)

Dimitris Lymperopoulos, Maria Lymperaiou, Giorgos Filandrianos, Giorgos Stamou

AI总结:

针对NLP模型可解释性需求,本研究提出基于图神经网络的文本反事实生成框架,通过语义编辑输入改变模型预测以提供反事实解释,在两项任务上验证了其编辑的对比性、流畅性、最小改动性及更优的速度表现。

摘要:

随着NLP模型在决策流程中变得愈发不可或缺,对可解释性与可解读性的需求已变得至关重要。在本研究中,我们提出了一个框架,通过生成经过语义编辑的输入(即反事实干预)来实现上述目标,这类输入能够改变模型的预测结果,从而为模型提供一种反事实解释形式。我们在两项NLP任务——二分类情感分类与主题分类——上测试了该框架,结果表明生成的编辑内容具有对比性、流畅性且改动量极小,同时整个过程的速度显著快于其他当前最优的反事实编辑器。

英文摘要:

As NLP models become increasingly integral to decision-making processes, the need for explainability and interpretability has become paramount. In this work, we propose a framework that achieves the aforementioned by generating semantically edited inputs, known as counterfactual interventions, which change the model prediction, thus providing a form of counterfactual explanations for the model. We test our framework on two NLP tasks - binary sentiment classification and topic classification - and show that the generated edits are contrastive, fluent and minimal, while the whole process remains significantly faster that other state-of-the-art counterfactual editors.

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。

↑