SIDU-TXT: An XAI Algorithm for NLP with a Holistic Assessment Approach

• URL: http://arxiv.org/abs/2402.03043v1
• Date: Mon, 5 Feb 2024 14:29:54 GMT
• Title: SIDU-TXT: An XAI Algorithm for NLP with a Holistic Assessment Approach
• Authors: Mohammad N.S. Jahromi, Satya. M. Muddamsetty, Asta Sofie Stage Jarlner, Anna Murphy H{\o}genhaug, Thomas Gammeltoft-Hansen, Thomas B. Moeslund
• Abstract summary: '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. We find that, in sentiment analysis task of a movie review dataset, SIDU-TXT excels in both functionally and human-grounded evaluations.
• Score: 14.928572140620245
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Developing Guidelines for Functionally-Grounded Evaluation of Explainable Artificial Intelligence using Tabular Data [5.864471607396997]
  We identify 20 evaluation criteria and associated evaluation methods, and derive guidelines on when and how each criterion should be evaluated. Our study contributes to the body of knowledge on XAI evaluation through in-depth examination of functionally-grounded XAI evaluation protocols.
  arXiv  Detail & Related papers  (2024-09-30T11:42:54Z)
• SCENE: Evaluating Explainable AI Techniques Using Soft Counterfactuals [0.0]
  This paper introduces SCENE (Soft Counterfactual Evaluation for Natural language Explainability), a novel evaluation method. By focusing on token-based substitutions, SCENE creates contextually appropriate and semantically meaningful Soft Counterfactuals. SCENE provides valuable insights into the strengths and limitations of various XAI techniques.
  arXiv  Detail & Related papers  (2024-08-08T16:36:24Z)
• A Comprehensive Survey on Underwater Image Enhancement Based on Deep Learning [51.7818820745221]
  Underwater image enhancement (UIE) presents a significant challenge within computer vision research. Despite the development of numerous UIE algorithms, a thorough and systematic review is still absent.
  arXiv  Detail & Related papers  (2024-05-30T04:46:40Z)
• Exploring the Power of Topic Modeling Techniques in Analyzing Customer Reviews: A Comparative Analysis [0.0]
  Machine learning and natural language processing algorithms have been deployed to analyze the vast amount of textual data available online. In this study, we examine and compare five frequently used topic modeling methods specifically applied to customer reviews. Our findings reveal that BERTopic consistently yield more meaningful extracted topics and achieve favorable results.
  arXiv  Detail & Related papers  (2023-08-19T08:18:04Z)
• REX: Rapid Exploration and eXploitation for AI Agents [103.68453326880456]
  We propose an enhanced approach for Rapid Exploration and eXploitation for AI Agents called REX. REX introduces an additional layer of rewards and integrates concepts similar to Upper Confidence Bound (UCB) scores, leading to more robust and efficient AI agent performance.
  arXiv  Detail & Related papers  (2023-07-18T04:26:33Z)
• An Experimental Investigation into the Evaluation of Explainability Methods [60.54170260771932]
  This work compares 14 different metrics when applied to nine state-of-the-art XAI methods and three dummy methods (e.g., random saliency maps) used as references. Experimental results show which of these metrics produces highly correlated results, indicating potential redundancy.
  arXiv  Detail & Related papers  (2023-05-25T08:07:07Z)
• Connecting Algorithmic Research and Usage Contexts: A Perspective of Contextualized Evaluation for Explainable AI [65.44737844681256]
  A lack of consensus on how to evaluate explainable AI (XAI) hinders the advancement of the field. We argue that one way to close the gap is to develop evaluation methods that account for different user requirements.
  arXiv  Detail & Related papers  (2022-06-22T05:17:33Z)
• A Simple Information-Based Approach to Unsupervised Domain-Adaptive Aspect-Based Sentiment Analysis [58.124424775536326]
  We propose a simple but effective technique based on mutual information to extract their term. Experiment results show that our proposed method outperforms the state-of-the-art methods for cross-domain ABSA by 4.32% Micro-F1.
  arXiv  Detail & Related papers  (2022-01-29T10:18:07Z)
• Introducing and assessing the explainable AI (XAI)method: SIDU [17.127282412294335]
  We present a novel XAI visual explanation algorithm denoted SIDU that can effectively localize entire object regions. We analyze its robustness and effectiveness through various computational and human subject experiments.
  arXiv  Detail & Related papers  (2021-01-26T11:13:50Z)
• Why model why? Assessing the strengths and limitations of LIME [0.0]
  This paper examines the effectiveness of the Local Interpretable Model-Agnostic Explanations (LIME) xAI framework. LIME is one of the most popular model agnostic frameworks found in the literature. We show how LIME can be used to supplement conventional performance assessment methods.
  arXiv  Detail & Related papers  (2020-11-30T21:08:07Z)
• SAMBA: Safe Model-Based & Active Reinforcement Learning [59.01424351231993]
  SAMBA is a framework for safe reinforcement learning that combines aspects from probabilistic modelling, information theory, and statistics. We evaluate our algorithm on a variety of safe dynamical system benchmarks involving both low and high-dimensional state representations. We provide intuition as to the effectiveness of the framework by a detailed analysis of our active metrics and safety constraints.
  arXiv  Detail & Related papers  (2020-06-12T10:40:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.