As neural-network-based QA models become deeper and more complex, there is a demand for robust frameworks which can access a model's rationale for its prediction. Current techniques that provide insights on a model's working are either dependent on adversarial datasets or are proposing models with explicit explanation generation components. These techniques are time-consuming and challenging to extend to existing models and new datasets. In this work, we use `Integrated Gradients' to extract rationale for existing state-of-the-art models in the task of Reading Comprehension based Question Answering (RCQA). On detailed analysis and comparison with collected human rationales, we find that though ~40-80% words of extracted rationale coincide with the human rationale (precision), only 6-19% of human rationale is present in the extracted rationale (recall).
翻译:随着以神经网络为基础的质量评估模型变得更加深入和复杂,人们需要强有力的框架,以获得模型的预测依据。目前为模型工作提供洞察力的技术要么依赖于对立数据集,要么正在提出具有明确解释生成组成部分的模型。这些技术耗费时间,难以推广到现有的模型和新的数据集。在这项工作中,我们使用“综合梯度”来为基于综合回答问题的答案(RCQA)任务的现有最新模型寻找理由。关于与所收集的人类原理的详细分析和比较,我们发现,尽管提取原理的~40-80%的字词与人类原理(精准)相吻合,但在提取的理由(回顾)中只存在人类原理的6-19%。