论文标题
Adalogn：用于基于推理的机器阅读理解的自适应逻辑图网络
AdaLoGN: Adaptive Logic Graph Network for Reasoning-Based Machine Reading Comprehension
论文作者
论文摘要
最近的机器阅读理解数据集（例如Reclor和LogiQa）需要对文本执行逻辑推理。常规的神经模型不足以用于逻辑推理，而符号推理器不能直接应用于文本。为了应对挑战，我们提出了一种神经符号方法，该方法为了预测答案，将消息传递到代表文本单元之间逻辑关系的图表上。它结合了一个自适应逻辑图网络（ADALOGN），该网络可自适应地侵入逻辑关系以扩展图形，从本质上讲，在神经和符号推理之间实现了相互和迭代的增强。我们还实施了一种新颖的子图形消息传递机制，以增强上下文选择交互，以回答多项选择问题。我们的方法显示了Reclor和LogiQA的有希望的结果。
Recent machine reading comprehension datasets such as ReClor and LogiQA require performing logical reasoning over text. Conventional neural models are insufficient for logical reasoning, while symbolic reasoners cannot directly apply to text. To meet the challenge, we present a neural-symbolic approach which, to predict an answer, passes messages over a graph representing logical relations between text units. It incorporates an adaptive logic graph network (AdaLoGN) which adaptively infers logical relations to extend the graph and, essentially, realizes mutual and iterative reinforcement between neural and symbolic reasoning. We also implement a novel subgraph-to-node message passing mechanism to enhance context-option interaction for answering multiple-choice questions. Our approach shows promising results on ReClor and LogiQA.
