[论文解读] Uncertainty in Natural Language Processing: Sources, Quantification, and Applications

Mengting Hu, Zhen Zhang+3 more|arXiv (Cornell University)|Jun 5, 2023

Explainable Artificial Intelligence (XAI)被引用 11

一句话总结

对NLP中的不确定性进行全面综述，概述跨输入、系统和输出的来源，调查估计方法，并回顾应用与挑战。

ABSTRACT

As a main field of artificial intelligence, natural language processing (NLP) has achieved remarkable success via deep neural networks. Plenty of NLP tasks have been addressed in a unified manner, with various tasks being associated with each other through sharing the same paradigm. However, neural networks are black boxes and rely on probability computation. Making mistakes is inevitable. Therefore, estimating the reliability and trustworthiness (in other words, uncertainty) of neural networks becomes a key research direction, which plays a crucial role in reducing models' risks and making better decisions. Therefore, in this survey, we provide a comprehensive review of uncertainty-relevant works in the NLP field. Considering the data and paradigms characteristics, we first categorize the sources of uncertainty in natural language into three types, including input, system, and output. Then, we systemically review uncertainty quantification approaches and the main applications. Finally, we discuss the challenges of uncertainty estimation in NLP and discuss potential future directions, taking into account recent trends in the field. Though there have been a few surveys about uncertainty estimation, our work is the first to review uncertainty from the NLP perspective.

研究动机与目标

• 识别并对NLP在输入、系统和输出阶段的不确定性来源进行分类。
• 评估在NLP中使用的现有不确定性量化方法，并将其与模型特征相关联。
• 概述NLP中不确定性估计的当前应用，讨论挑战与未来方向。

提出的方法

• 按NLP系统阶段（输入、系统、输出）对不确定性源进行分类，并讨论 aleatoric vs epistemic 不确定性。
• 回顾三种主要不确定性估计方法：基于校准的、基于采样的、基于分布的方法。
• 概述典型评估指标并讨论校准技术，如 Softmax-based 指标、温度缩放、标签平滑和 conformal prediction。
• 综合应用于数据过滤/行动指导、性能/效率提升以及输出质量评估。

Figure 1: An illustration of NLP systems applied in the medical domain.

实验结果

研究问题

• RQ1 NLP 系统在输入、系统和输出阶段的主要不确定性来源有哪些？
• RQ2 哪些不确定性估计技术最适用于 NLP，以及它们如何与模型设计和任务类型相关？
• RQ3 在分类、序列标注、生成和回归等 NLP 任务中，不确定性估计方法是如何应用的？
• RQ4 使用现代 PLMs 的 NLP 不确定性估计的关键挑战与未来方向有哪些？

主要发现

• NLP 中的不确定性源自输入模糊性、系统设计和输出复杂性之间的交织，需要同时考虑 aleatoric 与 epistemic 分量。
• NLP 中的不确定性估计可以分为基于校准的、基于采样的和基于分布的方法，每种方法各有优点和挑战。
• 类似 Softmax responses、熵、温度缩放、标签平滑和 conformal prediction 的校准方法有助于量化并可能纠正置信度估计。
• 不确定性的应用包括数据过滤与行动指引、提升系统性能/效率，以及评估输出质量和可信度。
• 大规模预训练模型的出现带来与模型规模、训练数据偏差以及超参数敏感性相关的新不确定性挑战。

Figure 2: Illustration of sources of uncertainty. The figure includes the sources of uncertainty in the interaction of the NLP system. We start from the three processes of Input , System , and Output to analyze the possible causes of each uncertainty. It is worth noting that these three parts are in