论文标题
通过层次图网络回答微调多跳的问题
Fine-tuning Multi-hop Question Answering with Hierarchical Graph Network
论文作者
论文摘要
在本文中，我们提出了一个两个阶段模型，用于回答多跳问题。第一阶段是一个层次图网络，用于对多跳问题进行推理，并能够使用文档的自然结构（即段落，问题，句子和实体）捕获不同级别的粒度。推理过程是转换为节点分类任务（即，段落节点和句子节点）。第二阶段是语言模型微调任务。在一个单词中，第一阶段使用图形神经网络选择和连接支持句子作为一个段落，第二阶段在语言模型微调范式中找到答案跨度。
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.
