Conversational question answering (CQA) is a novel QA task that requires understanding of dialogue context. Different from traditional single-turn machine reading comprehension (MRC) tasks, CQA includes passage comprehension, coreference resolution, and contextual understanding. In this paper, we propose an innovated contextualized attention-based deep neural network, SDNet, to fuse context into traditional MRC models. Our model leverages both inter-attention and self-attention to comprehend conversation context and extract relevant information from passage. Furthermore, we demonstrated a novel method to integrate the latest BERT contextual model. Empirical results show the effectiveness of our model, which sets the new state of the art result in CoQA leaderboard, outperforming the previous best model by 1.6% F1. Our ensemble model further improves the result by 2.7% F1.

翻译：解答问题解答( CQA) 是一项新颖的QA任务, 需要理解对话背景。 不同于传统的单极机器阅读理解( MRC) 任务, CQA 包括通过理解、 引用分辨率和背景理解。 在本文中, 我们提出一个创新的基于背景的深层神经网络, SDNet, 将环境结合到传统的 MRC 模型中。 我们的模型利用关注和自我意识来理解对话背景, 并从中提取相关信息。 此外, 我们展示了将最新的 BERT 环境模型整合起来的新方法。 经验性结果展示了我们的模型的有效性, 它为 CoQA 领导板设定了艺术成果的新状态, 超过了1.6 % F1. 我们的组合模型, 进一步改进了2. 7 % F1的结果。