摘要
从单文档中生成简短精炼的摘要文本可有效缓解信息爆炸给人们带来的阅读压力。近年来,序列到序列(sequence-to-sequence,Seq2Seq)模型在各文本生成任务中广泛应用,其中结合注意力机制的Seq2Seq模型已成为生成式文本摘要的基本框架。为生成能体现摘要的特定写作风格特征的摘要,在基于注意力和覆盖率机制的Seq2Seq模型基础上,在解码阶段利用变分自编码器(variational auto-encoder,VAE)刻画摘要风格特征并用于指导摘要文本生成;最后,利用指针生成网络来缓解模型中可能出现的未登录词问题。基于新浪微博LCSTS数据集的实验结果表明,该方法能有效刻画摘要风格特征、缓解未登录词及重复生成问题,使得生成的摘要准确性高于基准模型。
Generate a brief and short summary for a document can effectively alleviate the reading pressure brought by information explosion.In recent years,Seq2Seq model has been widely applied in various text summarization.Especially,Seq2Seq with attention model has become a basic framework for abstractive text generation.To make the generated summary reflect the abstractive feature,this paper proposed a novel framework,which employed Seq2Seq model with attention and coverage mechanism as basic model,and used VAE to depict the latent feature in decoding process.At last,this paper used a pointer-generator network for relieving the out-of-vocabulary(OOV)problem to generate the summary tokens successively.Experimental results on the LCSTS dataset demonstrate that the proposed framework is able to capture the latent feature of summary text and relief the OOV and tokens repetition problem,thus generating more accurate and readable summary.
作者
黄佳佳
李鹏伟
Huang Jiajia;Li Pengwei(School of Information Engineering,Nanjing Audit University,Nanjing 211815,China)
出处
《计算机应用研究》
CSCD
北大核心
2021年第3期705-709,共5页
Application Research of Computers
基金
国家自然科学基金资助项目(61802194,61902190)
江苏省高等学校自然科学研究项目(17KJB520015,19KJB520040)。
关键词
文本摘要
变分自编码器
Seq2Seq模型
覆盖率机制
指针生成网络
abstractive text summarization
variational auto-encoder(VAE)
Seq2Seq model
coverage mechanism
pointer-generator network
作者简介
通信作者:黄佳佳(1989-),女,安徽六安人,讲师,博士,主要研究方向为自然语言处理、审计数据分析(huangjj@nau.edu.cn);李鹏伟(1987-),男,讲师,博士,主要研究方向为软件安全与数据分析.
