A framework for evaluating and explaining the robustness of NLP models

评估和解释 NLP 模型稳健性的框架

• 批准号: EP/X04162X/1
• 负责人: Oana Cocarascu
• 金额: $ 40.55万
• 依托单位: King's College London
• 依托单位国家: 英国
• 项目类别: Research Grant
• 财政年份: 2024
• 资助国家: 英国
• 起止时间: 2024 至 无数据
• 项目状态: 未结题
• 来源: https://gtr.ukri.org/projects?ref=EP%2FX04162X%2F1
• 关键词: framework; evaluating; explaining; robustness; NLP

The standard practice for evaluating the generalisation of supervised machine learning models in NLP tasks is to use previously unseen (i.e. held-out) data and report the performance on it using various metrics such as accuracy. Whilst metrics reported on held-out data summarise a model's performance, ultimately these results represent aggregate statistics on benchmarks and do not reflect the nuances in model behaviour and robustness when applied in real-world systems.We propose a robustness evaluation framework for NLP models concerned with arguments and facts, which encompasses explanations for robustness failures to support systematic and efficient evaluation. We will develop novel methods for simulating real-world texts stemming from existing datasets, to help evaluate the stability and consistency of models when deployed in the wild. The simulation methods will be used to challenge NLP models through text-based transformations and distribution shifts on datasets as well as on data sub-sets that capture linguistic patterns, to provide a systematic coverage of real-world linguistic phenomena. Furthermore, our framework will shed insights into a model's robustness by generating explanations for robustness failures along the lexical, morphological, and syntactic dimensions, extracted from the various dataset simulations and data sub-sets, thus departing from current approaches that solely provide a metric to quantify robustness. We will focus on two NLP research areas, argument mining and fact verification, however, several simulation methods and the robustness explanations are also scalable to other NLP tasks.

评估NLP任务中监督机器学习模型的概括的标准实践是使用以前看不见的数据（即保留）数据，并使用各种指标（例如准确性）报告其性能。虽然在持有数据中报告的指标总结了模型的性能，但最终这些结果代表了基准的总统计数据，并且在现实世界中应用模型和鲁棒性的细微差别并不反映在现实世界系统中的差异。我们提出了与参数有关的NLP鲁棒性评估框架，以构成了与鲁棒性的识别，并有效地对其进行了支持，并有效地构成了对鲁棒性的影响，并有效地支持了系统。我们将开发新的方法，用于模拟来自现有数据集的现实世界文本，以帮助评估在野外部署时模型的稳定性和一致性。模拟方法将用于通过基于文本的转换和数据集的分布变化以及捕获语言模式的数据子集的分配变化来挑战NLP模型，以提供对现实世界语言现象的系统覆盖。此外，我们的框架将通过产生沿词汇，形态学和句法维度的鲁棒性失败的解释来洞悉模型的鲁棒性，从各种数据集模拟和数据子集中提取，从而偏离了仅提供量化鲁棒性的当前方法。我们将重点关注两个NLP研究领域，即挖掘和事实验证，但是，几种模拟方法和鲁棒性解释也可扩展到其他NLP任务。