Multi-choice Machine Reading Comprehension (MRC) as a challenge requires models to select the most appropriate answer from a set of candidates with a given passage and question. Most of the existing researches focus on the modeling of specific tasks or complex networks, without explicitly referring to relevant and credible external knowledge sources, which are supposed to greatly make up for the deficiency of the given passage. Thus we propose a novel reference-based knowledge enhancement model called Reference Knowledgeable Network (RekNet), which simulates human reading strategies to refine critical information from the passage and quote explicit knowledge in necessity. In detail, RekNet refines fine-grained critical information and defines it as Reference Span, then quotes explicit knowledge quadruples by the co-occurrence information of Reference Span and candidates. The proposed RekNet is evaluated on three multi-choice MRC benchmarks: RACE, DREAM and Cosmos QA, obtaining consistent and remarkable performance improvement with observable statistical significance level over strong baselines. Our code is available at https://github.com/Yilin1111/RekNet.

中文翻译：

---

机器阅读理解的参考知识网络


多选机器阅读理解（MRC）作为一项挑战，要求模型从给定段落和问题的一组候选者中选择最合适的答案。现有的研究大多集中在特定任务或复杂网络的建模上，没有明确参考相关且可信的外部知识源，这应该可以极大地弥补给定文章的不足。因此，我们提出了一种新颖的基于参考的知识增强模型，称为参考知识网络（RekNet），它模拟人类阅读策略，从文章中提炼关键信息，并在必要时引用显性知识。具体来说，RekNet提炼细粒度的关键信息并将其定义为Reference Span，然后通过Reference Span和候选者的共现信息引用显性知识四倍体。所提出的 RekNet 在三个多选择 MRC 基准上进行评估：RACE、DREAM 和 Cosmos QA，获得了一致且显着的性能改进，并且在强基线上具有可观察到的统计显着性水平。我们的代码可在 https://github.com/Yilin1111/RekNet 获取。