SIDU-TXT：一种具有整体评估方法的自然语言处理XAI算法
SIDU-TXT: An XAI Algorithm for NLP with a Holistic Assessment Approach
AI总结：
本文提出SIDU-TXT，一种将SIDU方法扩展到文本数据的XAI算法，通过词级热图提供解释，并在情感分析中优于Grad-CAM和LIME，但在法律领域仍需改进。
摘要：
可解释人工智能（XAI）有助于解读“黑箱”模型。尽管已有多种方法主要在图像领域被提出和评估，但在文本领域的可解释性探索仍是一个不断发展的研究领域。本文深入探讨了XAI方法在文本领域的适用性。在此背景下，将“相似性差异与独特性”（SIDU）XAI方法扩展到文本数据，该方法在基于图像的分类中以其在定位整个显著区域方面的卓越能力而著称。扩展后的方法SIDU-TXT利用“黑箱”模型的特征激活图，在细粒度的单词级别生成热图，从而提供突出对模型预测至关重要的上下文显著文本元素的解释。鉴于缺乏评估XAI方法的统一标准，本研究应用了一个整体的三层综合评估框架：功能基础、人类基础和应用程序基础，以评估所提出的SIDU-TXT在各种实验中的有效性。我们发现，在电影评论数据集的情感分析任务中，SIDU-TXT在功能基础和人类基础评估中均表现出色，通过定量和定性分析，与Grad-CAM和LIME等基准相比，展示了优越的性能。在敏感且复杂的法律领域——庇护决策中的应用基础评估中，SIDU-TXT和Grad-CAM表现出相当的性能，各有其优缺点。然而，这两种方法都未能完全满足专家期望的复杂标准，凸显了对此类领域适用的XAI方法进行额外研究的迫切需要。
英文摘要：
Explainable AI (XAI) aids in deciphering 'black-box' models. While several methods have been proposed and evaluated primarily in the image domain, the exploration of explainability in the text domain remains a growing research area. In this paper, we delve into the applicability of XAI methods for the text domain. In this context, the 'Similarity Difference and Uniqueness' (SIDU) XAI method, recognized for its superior capability in localizing entire salient regions in image-based classification is extended to textual data. The extended method, SIDU-TXT, utilizes feature activation maps from 'black-box' models to generate heatmaps at a granular, word-based level, thereby providing explanations that highlight contextually significant textual elements crucial for model predictions. Given the absence of a unified standard for assessing XAI methods, this study applies a holistic three-tiered comprehensive evaluation framework: Functionally-Grounded, Human-Grounded and Application-Grounded, to assess the effectiveness of the proposed SIDU-TXT across various experiments. We find that, in sentiment analysis task of a movie review dataset, SIDU-TXT excels in both functionally and human-grounded evaluations, demonstrating superior performance through quantitative and qualitative analyses compared to benchmarks like Grad-CAM and LIME. In the application-grounded evaluation within the sensitive and complex legal domain of asylum decision-making, SIDU-TXT and Grad-CAM demonstrate comparable performances, each with its own set of strengths and weaknesses. However, both methods fall short of entirely fulfilling the sophisticated criteria of expert expectations, highlighting the imperative need for additional research in XAI methods suitable for such domains.
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。
