基于语法规律的相关材料标记模型  

A Relevant Evidence Labeling Model Based on Grammatical Rules

作　　者：吴锐帆 WU Rui-fan(School of Mathematical Sciences,South China Normal University,Guangzhou,Guangdong,510000)

机构地区：[1]华南师范大学数学科学学院,广东广州510000

出　　处：《韩山师范学院学报》2018年第3期27-34,共8页Journal of Hanshan Normal University

摘　　要：建立了一个基于中文语法规律的相关材料标记模型.该模型可根据问题在材料中标记出与问题相关的段落.主要步骤包括:(1)根据问题语法进行问题分类,进而将问题划分到不同类型的问题处理模型中;(2)对问题进行关键词提取以确定问题核心内容;(3)根据问题类型与关键词,从材料中搜索候选答案并进行筛选;(4)根据候选答案进行相关段落标记.在百度的中文问答数据集Web QA上进行测试,得到的结果接近循环神经网络标记模型,并且具有较高的可解释性.This paper has set up a relevant evidences labeling model based on Chinese grammatical rules.The model can label the relevant evidence in the text according to the question.The new model contains the following essential phases:(1)classifying the question with the grammar of question to different submodels,(2)confirming the primary coverage of question by keywords extraction,(3)searching and screening the an?swers in the text on the basis of question classification and keyword extraction,(4)labeling the relevant evi?dences.Tests on the dataset WebQA(proposed by Baidu)show that the model has a similar result with the neural recurrent sequence labeling model,while the new model has the better interpretability.

关 键 词：智能阅读 语法规律 标记模型 答案检索 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]