arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.13821cs.CLcs.AIcs.LG
收藏

基于分层图网络微调多跳问答

Fine-tuning Multi-hop Question Answering with Hierarchical Graph Network

Guanming Xiong

AI总结:

针对多跳问答问题,本文提出两阶段模型:第一阶段通过分层图网络利用文档结构捕捉不同粒度并转化为节点分类任务以筛选拼接支持句,第二阶段基于语言模型微调寻找答案跨度,提升多跳推理与答案定位能力。

摘要:

本文提出一种两阶段多跳问答模型。第一阶段为分层图网络,用于对多跳问题进行推理,能利用文档的自然结构(即段落、问题、句子和实体)捕捉不同粒度层次;推理过程被转化为节点分类任务(即段落节点和句子节点)。第二阶段为语言模型微调任务。简言之,第一阶段利用图神经网络选择并拼接支持句为一个段落,第二阶段在语言模型微调范式中寻找答案跨度。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑