In this paper, we present a two stage model for multi-hop question answering. The first stage is a hierarchical graph network, which is used to reason over multi-hop question and is capable to capture different levels of granularity using the nature structure(i.e., paragraphs, questions, sentences and entities) of documents. The reasoning process is convert to node classify task(i.e., paragraph nodes and sentences nodes). The second stage is a language model fine-tuning task. In a word, stage one use graph neural network to select and concatenate support sentences as one paragraph, and stage two find the answer span in language model fine-tuning paradigm.
翻译:在本文中,我们提出了一个多跳问题解答的两阶段模式。 第一阶段是一个等级图网络, 用于解释多跳问题, 并且能够利用文件的自然结构( 即段落、 问题、 句子和实体) 捕捉不同程度的颗粒。 推理过程转换为节点分类任务( 即节点和句子节点) 。 第二阶段是一个语言模型微调任务 。 在一个单词中, 第一阶段使用图形神经网络选择和将支持句子合并为一款, 第二阶段在语言模型微调模式中找到答案范围 。