arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2110.04620cs.CLcs.AI
收藏

一种用于深度QA模型的基本原理提取框架

A Framework for Rationale Extraction for Deep QA models

Robert Bosch Centre for Data Science and AI (RBC-DSAI)(罗伯特·博世数据科学与人工智能中心(RBC-DSAI));Indian Institute of Technology Madras(印度理工学院马德拉斯分校);Google Research(谷歌研究院)

Sahana Ramnath, Preksha Nema, Deep Sahni, Mitesh M. Khapra

摘要:

随着基于神经网络的QA模型变得更深入、更复杂,人们需要一个强大的框架来访问模型的预测原理。目前提供模型工作洞察的技术要么依赖于对抗性数据集,要么提出具有显式解释生成组件的模型。这些技术是耗时和具有挑战性的扩展到现有的模型和新的数据集。在这项工作中,我们使用“集成的先决条件”,以提取现有的国家的最先进的模式在阅读理解为基础的问答(RCQA)的任务的基本原理。在详细的分析和与收集的人类理性的比较,我们发现,虽然约40-80%的词提取的理性与人类的理性(精度)相吻合,只有6-19%的人类理性是存在于提取的理性(召回)。

英文摘要:

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).

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑