论文标题
基于进化算法的自动提问框架
An Automated Question-Answering Framework Based on Evolution Algorithm
论文作者
论文摘要
为提问（QA）任务建立一个深度学习模型需要大量的人类努力，可能需要几个月的时间来仔细调整各种模型架构并找到最佳的模型。为多个数据集找到不同的出色模型甚至更难。最近的作品表明，最佳模型结构与所使用的数据集有关，并且一个模型无法适应所有任务。在本文中，我们提出了一个自动提问框架，该框架可以自动调整多个数据集的网络体系结构。我们的框架基于一种创新的进化算法，该算法稳定且适合多个数据集方案。搜索的演化算法将先验知识结合到初始人群中，并使用性能估计器通过预测候选模型体系结构的性能来避免效率低下的突变。初始人群中使用的先验知识可以改善进化算法的最终结果。随着试验数量的增加，绩效估计器可以迅速滤除人群中绩效不佳的模型，以加快收敛速度。我们的框架在小队1.1、69.9 EM和Squad 2.0上的Squad 1.1、69.9 EM和72.5 F1上实现了78.9 EM和86.1 F1。在NewsQA数据集上，找到的模型可实现47.0 EM和62.9 F1。
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.
