Visual Interrogation of Attention-Based Models for Natural Language Inference and Machine Comprehension
Visual Interrogation of Attention-Based Models for Natural Language Inference and Machine Comprehension
复制标题
用于自然语言推理和机器理解的基于注意力的模型的视觉询问
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
P. Bremer
中科院分区：
文献类型：
--
作者：
Shusen Liu;Tao Li;Zhimin Li;Vivek Srikumar;Valerio Pascucci;P. Bremer
神经网络模型因其最先进的性能和灵活的端到端训练方案而在自然语言处理中获得了前所未有的欢迎。尽管它们具有优势，但缺乏可解释性阻碍了模型的部署和改进。在这项工作中，我们提出了一个灵活的可视化库来创建定制的可视化分析环境，在这个库中，用户可以调查和询问输入、模型内部(即注意力)和输出预测之间的关系，这反过来又揭示了模型决策过程。
Neural networks models have gained unprecedented popularity in natural language processing due to their state-of-the-art performance and the flexible end-to-end training scheme. Despite their advantages, the lack of interpretability hinders the deployment and refinement of the models. In this work, we present a flexible visualization library for creating customized visual analytic environments, in which the user can investigate and interrogate the relationships among the input, the model internals (i.e., attention), and the output predictions, which in turn shed light on the model decision-making process.