Explaining machine learning models with interactive natural language conversations using TalkToModel
Explaining machine learning models with interactive natural language conversations using TalkToModel
复制标题
使用TalkToModel通过交互式自然语言对话解释机器学习模型
DOI：
10.1038/s42256-023-00692-8
复制
发表时间：
2022-07
影响因子：
23.8
通讯作者：
Dylan Slack;Satyapriya Krishna;Himabindu Lakkaraju;Sameer Singh
中科院分区：
文献类型：
--
作者：
Dylan Slack;Satyapriya Krishna;Himabindu Lakkaraju;Sameer Singh
从业者越来越多地使用机器学习（ML）模型，但模型变得越来越复杂，越来越难以理解。为了理解复杂的模型，研究人员提出了解释模型预测的技术。然而，实践者努力使用可解释性方法，因为他们不知道选择哪种解释以及如何解释解释。在这里，我们通过提出TalkToModel来解决使用可解释性方法的挑战：一个通过自然语言对话解释ML模型的交互式对话系统。TalkToModel由三个组件组成：自适应对话引擎，用于解释自然语言并生成有意义的响应;执行组件，用于构建对话中使用的解释;以及会话界面。在现实世界的评估中，73%的医疗工作者同意他们将使用TalkToModel而不是现有系统来理解疾病预测模型，85%的ML专业人员同意TalkToModel更容易使用，这表明TalkToModel对于模型的可解释性非常有效。
Practitioners increasingly use machine learning (ML) models, yet models have become more complex and harder to understand. To understand complex models, researchers have proposed techniques to explain model predictions. However, practitioners struggle to use explainability methods because they do not know which explanation to choose and how to interpret the explanation. Here we address the challenge of using explainability methods by proposing TalkToModel: an interactive dialogue system that explains ML models through natural language conversations. TalkToModel consists of three components: an adaptive dialogue engine that interprets natural language and generates meaningful responses; an execution component that constructs the explanations used in the conversation; and a conversational interface. In real-world evaluations, 73% of healthcare workers agreed they would use TalkToModel over existing systems for understanding a disease prediction model, and 85% of ML professionals agreed TalkToModel was easier to use, demonstrating that TalkToModel is highly effective for model explainability.