QADiver: Interactive Framework for Diagnosing QA Models
QADiver: Interactive Framework for Diagnosing QA Models
复制标题
QADiver：诊断 QA 模型的交互式框架
DOI：
10.1609/aaai.v33i01.33019861
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Seung
中科院分区：
文献类型：
--
作者：
Gyeongbok Lee;Sungdong Kim;Seung
问答（QA）从文本中提取自然语言中给定问题的答案，已经得到了积极的研究，现有的模型在使用SQuAD数据集进行训练和评估时，表现出优于人类的性能。然而，这样的性能在实际设置中可能无法复制，为此我们需要诊断原因，由于模型的复杂性，这是不平凡的。因此，我们提出了一个基于Web的用户界面，提供每个模型如何有助于QA性能，通过集成可视化和分析工具的模型解释。我们希望这个框架可以帮助QA模型研究人员完善和改进他们的模型。
Question answering (QA) extracting answers from text to the given question in natural language, has been actively studied and existing models have shown a promise of outperforming human performance when trained and evaluated with SQuAD dataset. However, such performance may not be replicated in the actual setting, for which we need to diagnose the cause, which is non-trivial due to the complexity of model. We thus propose a web-based UI that provides how each model contributes to QA performances, by integrating visualization and analysis tools for model explanation. We expect this framework can help QA model researchers to refine and improve their models.