Automatic text summarization(ATS)has achieved impressive performance thanks to recent advances in deep learning(DL)and the availability of large-scale corpora.The key points in ATS are to estimate the salience of info...Automatic text summarization(ATS)has achieved impressive performance thanks to recent advances in deep learning(DL)and the availability of large-scale corpora.The key points in ATS are to estimate the salience of information and to generate coherent results.Recently,a variety of DL-based approaches have been developed for better considering these two aspects.However,there is still a lack of comprehensive literature review for DL-based ATS approaches.The aim of this paper is to comprehensively review significant DL-based approaches that have been proposed in the literature with respect to the notion of generic ATS tasks and provide a walk-through of their evolution.We first give an overview of ATS and DL.The comparisons of the datasets are also given,which are commonly used for model training,validation,and evaluation.Then we summarize single-document summarization approaches.After that,an overview of multi-document summarization approaches is given.We further analyze the performance of the popular ATS models on common datasets.Various popular approaches can be employed for different ATS tasks.Finally,we propose potential research directions in this fast-growing field.We hope this exploration can provide new insights into future research of DL-based ATS.展开更多
基金This work was partially supported by grants-in-aid from Social Science Foundation of Chinese Ministry of Education （No. 06JJD740007）, Project of Shandong Social Science Fund （No. 07CWXJ03）.
基金supported by the National Key Research and Development Program of China under Grant No.2016YFB1000902the National Natural Science Foundation of China under Grant Nos.61232015,61472412,and 61621003.
文摘Automatic text summarization(ATS)has achieved impressive performance thanks to recent advances in deep learning(DL)and the availability of large-scale corpora.The key points in ATS are to estimate the salience of information and to generate coherent results.Recently,a variety of DL-based approaches have been developed for better considering these two aspects.However,there is still a lack of comprehensive literature review for DL-based ATS approaches.The aim of this paper is to comprehensively review significant DL-based approaches that have been proposed in the literature with respect to the notion of generic ATS tasks and provide a walk-through of their evolution.We first give an overview of ATS and DL.The comparisons of the datasets are also given,which are commonly used for model training,validation,and evaluation.Then we summarize single-document summarization approaches.After that,an overview of multi-document summarization approaches is given.We further analyze the performance of the popular ATS models on common datasets.Various popular approaches can be employed for different ATS tasks.Finally,we propose potential research directions in this fast-growing field.We hope this exploration can provide new insights into future research of DL-based ATS.
文摘浅层狄利赫雷分配(Latent Dirichlet Allocation,LDA)方法近年来被广泛应用于文本聚类、分类、段落切分等等,并且也有人将其应用于基于提问的无监督的多文档自动摘要。该方法被认为能较好地对文本进行浅层语义建模。该文在前人工作基础上提出了基于LDA的条件随机场(Conditional Random Field,CRF)自动文摘(LCAS)方法,研究了LDA在有监督的单文档自动文摘中的作用,提出了将LDA提取的主题(Topic)作为特征加入CRF模型中进行训练的方法,并分析研究了在不同Topic下LDA对摘要结果的影响。实验结果表明,加入LDA特征后,能够有效地提高以传统特征为输入的CRF文摘系统的质量。
