可解释NLP的合理化：一项综述
Rationalization for Explainable NLP: A Survey
AI总结：
本综述系统梳理2007-2022年NLP中的合理化方法，涵盖技术、评估与数据集，并提出可解释AI新子领域理性AI（RAI），为未来研究指明方向。
摘要：
深度学习的最新进展提升了诸多自然语言处理（NLP）任务（如翻译、问答和文本分类）的性能。然而，这种提升是以模型可解释性为代价的。黑盒模型使得理解系统内部机制及其得出输出的过程变得困难。数值型（LIME、Shapley）和可视化（显著性热图）可解释性技术虽有帮助，但因其需要专业知识而显不足。这些因素促使合理化（rationalization）作为NLP中一种更易理解的可解释技术而出现。合理化通过提供自然语言解释（rationale）来证明模型输出的合理性。自然语言生成的最新进展使合理化成为一种有吸引力的技术，因为它直观、易于人类理解，且对非技术用户友好。由于合理化是一个相对较新的领域，其组织较为零散。作为首篇综述，本文分析了2007年至2022年间NLP中的合理化文献。本综述介绍了在采用合理化的各类NLP任务中所使用的现有方法、可解释性评估、代码和数据集。此外，本文引入了可解释人工智能（XAI）的一个新子领域，即理性人工智能（RAI），以推进合理化的当前状态。本文还讨论了对观察到的见解、挑战和未来方向的思考，以指出有前景的研究机会。
英文摘要：
Recent advances in deep learning have improved the performance of many Natural Language Processing (NLP) tasks such as translation, question-answering, and text classification. However, this improvement comes at the expense of model explainability. Black-box models make it difficult to understand the internals of a system and the process it takes to arrive at an output. Numerical (LIME, Shapley) and visualization (saliency heatmap) explainability techniques are helpful; however, they are insufficient because they require specialized knowledge. These factors led rationalization to emerge as a more accessible explainable technique in NLP. Rationalization justifies a model's output by providing a natural language explanation (rationale). Recent improvements in natural language generation have made rationalization an attractive technique because it is intuitive, human-comprehensible, and accessible to non-technical users. Since rationalization is a relatively new field, it is disorganized. As the first survey, rationalization literature in NLP from 2007-2022 is analyzed. This survey presents available methods, explainable evaluations, code, and datasets used across various NLP tasks that use rationalization. Further, a new subfield in Explainable AI (XAI), namely, Rational AI (RAI), is introduced to advance the current state of rationalization. A discussion on observed insights, challenges, and future directions is provided to point to promising research opportunities.
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。
