基于网络的动态多文档文摘系统框架  

Web-Based Dynamic Multi-Document Summarization System Framework

作　　者：刘美玲 任洪娥[1] 于洋[1] 郑德权 赵铁军[2] 

机构地区：[1]东北林业大学信息与计算机工程学院,黑龙江哈尔滨150040 [2]教育部-微软语言语音重点实验室(哈尔滨工业大学),黑龙江哈尔滨150001

出　　处：《软件学报》2013年第5期1006-1021,共16页Journal of Software

基　　金：国家自然科学基金(60736014;60773069;61073130);国家林业行业专项(201204715)

摘　　要：在自然语言处理和计算语言学相关技术支撑下,研究基于网络的动态多文档文摘系统框架,重点描述动态多文档文摘系统框架的相关内容,介绍利用矩阵子空间方法进行动态演化建模,利用相似度和质心整体优选计算方法进行信息过滤,并利用动态流形排序方法进行句子加权的动态多文档文摘生成系统.按照多文档文摘生成步骤的划分,对3种创新的模型方法进行融合,综合起来从不同侧重点考虑,形成互补,提高系统性能.在网络环境下,此框架保证了动态演化的多文档文摘具有较高的信息新颖性和历史信息的演化性.This paper introduces an Internet-based dynamic multi-document summarization system to support natural language processing and computational linguistics-related technical. This paper focuses on the description of the relevant content of dynamic multi-document summarization system framework and introduces dynamic evolutionary modeling using the matrix sub-space method, the information filtering model that uses the similarity and centroid integer selection method, and weighted sentence sorting, using the dynamic manifold method to generate the dynamic multi-document summarization system. This paper fuses the three innovation modeling methods to complement and to improve the performance of the system in accordance with the division of generated step of multi-document summarization. In a network environment, the framework ensures the dynamic evolutionary multi-document summarization with high novel information and evolutionary historical information.

关 键 词：模型框架 矩阵子空间 整体优选 动态演化 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]