检索结果-南通市图书馆

Enhancing N-Gram Based Metrics with Semantics for Better Evaluation of Abstractive Text Summarization

Journal of Computer Science & Technology 2022年第5期37卷 1118-1133页

作者： Jia-Wei He Wen-Jun Jiang Guo-Bang Chen Yu-Quan Le Xiao-Fei Ding College of Information Science and Electronic Engineering Hunan UniversityChangsha 410082China

Text summarization is an important task in natural language processing and it has been applied in many ***,abstractive summarization has attracted many ***,the traditional evaluation metrics that consider little semantic information,are unsuitable for evaluating the quality of deep learning based abstractive summarization models,since these models may generate new words that do not exist in the original ***,the out-of-vocabulary(OOV)problem that affects the evaluation results,has not been well solved *** address these issues,we propose a novel model called ENMS,to enhance existing N-gram based evaluation metrics with *** be specific,we present two types of methods:N-gram based Semantic matching(NSM for short),and N-gram based Semantic Similarity(NSS for short),to improve several widely-used evaluation metrics including ROUGE(Recall-Oriented Understudy for Gisting Evaluation),BLEU(Bilingual Evaluation Understudy),*** and NSS work in different *** former calculates the matching degree directly,while the latter mainly improves the similarity *** we propose an N-gram representation mechanism to explore the vector representation of N-grams(including skip-grams).It serves as the basis of our ENMS model,in which we exploit some simple but effective integration methods to solve the OOV problem *** results over the TAC AESOP dataset show that the metrics improved by our methods are well correlated with human judgements and can be used to better evaluate abstractive summarization methods.

关键词： summarization evaluation abstractive summarization hard matching semantic information

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：