Guided Structure-Aware Review Summarization  

作　　者：金锋 黄民烈 朱小燕 

机构地区：[1]State Key Laboratory of Intelligent Technology and Systems,Tsinghua National Laboratory for Information Science and Technology,Department of Computer Science and Technology,Tsinghua University

出　　处：《Journal of Computer Science & Technology》2011年第4期676-684,共9页计算机科学技术学报（英文版）

基　　金：supported by the National Natural Science Foundation of China under Grant Nos.60973104 and 60803075;with the aid of a grant from the International Development Research Center,Ottawa,Canada IRCI Project

摘　　要：Although the goal of traditional text summarization is to generate summaries with diverse information, most of those applications have no explicit definition of the information structure. Thus, it is difficult to generate truly structure-aware summaries because the information structure to guide summarization is unclear. In this paper, we present a novel framework to generate guided summaries for product reviews. The guided summary has an explicitly defined structure which comes from the important aspects of products. The proposed framework attempts to maximize expected aspect satisfaction during summary generation. The importance of an aspect to a generated summary is modeled using Labeled Latent Dirichlet Allocation. Empirical experimental results on consumer reviews of cars show the effectiveness of our method.Although the goal of traditional text summarization is to generate summaries with diverse information, most of those applications have no explicit definition of the information structure. Thus, it is difficult to generate truly structure-aware summaries because the information structure to guide summarization is unclear. In this paper, we present a novel framework to generate guided summaries for product reviews. The guided summary has an explicitly defined structure which comes from the important aspects of products. The proposed framework attempts to maximize expected aspect satisfaction during summary generation. The importance of an aspect to a generated summary is modeled using Labeled Latent Dirichlet Allocation. Empirical experimental results on consumer reviews of cars show the effectiveness of our method.

关 键 词：structure-aware summarization review mining topic model importance is modeled 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]