Building a deep learning model for a Question-Answering (QA) task requires a lot of human effort, it may need several months to carefully tune various model architectures and find a best one. It's even harder to find different excellent models for multiple datasets. Recent works show that the best model structure is related to the dataset used, and one single model cannot adapt to all tasks. In this paper, we propose an automated Question-Answering framework, which could automatically adjust network architecture for multiple datasets. Our framework is based on an innovative evolution algorithm, which is stable and suitable for multiple dataset scenario. The evolution algorithm for search combine prior knowledge into initial population and use a performance estimator to avoid inefficient mutation by predicting the performance of candidate model architecture. The prior knowledge used in initial population could improve the final result of the evolution algorithm. The performance estimator could quickly filter out models with bad performance in population as the number of trials increases, to speed up the convergence. Our framework achieves 78.9 EM and 86.1 F1 on SQuAD 1.1, 69.9 EM and 72.5 F1 on SQuAD 2.0. On NewsQA dataset, the found model achieves 47.0 EM and 62.9 F1.
翻译:为问题解答(QA)任务建立深层次学习模式需要大量人力努力,可能需要几个月的时间来仔细调整各种模型结构并找到最佳的模型。 找到不同优异的多数据集模型甚至更难。 最近的工作显示, 最佳模型结构与所使用的数据集相关, 一个单一模型无法适应所有任务。 在本文件中, 我们提议一个自动的问题解答框架, 它可以自动调整多个数据集的网络架构。 我们的框架基于创新的进化算法, 它稳定且适合多个数据集的设想。 用于搜索的进化算法将先前的知识结合到初始人群中, 使用性能估计器避免无效的突变, 预测候选模型结构的性能。 初始人群中使用的先前知识可以改善进化算法的最终结果。 性能测算器可以随着试验数量的增加而迅速筛选出人口表现不佳的模型, 以加快聚合速度。 我们的框架实现了78.9 QEM 和86.1 F1 QAD 1.1、29. 9 EM 和 FUA 1 在 SUA S. 090 A 上找到的S. 0A. 0A. 和 FU A. 0A. 0A. S. 0A. 0A. 0A. S. S. 9 找到的F. 和F. 1 IS. 1 和 F. 1 IS. 1 SA. 1 和 F. 0A. 1 SA. 0A.