An interpretive evaluation of entity summarization system

The task of entity summarization (ES) is to select an optimum subset from a large set of triples describing an entity in a knowledge graph.ES systems often integrate many and various ES features in a complex way.While state-of-the-art ES systems have been evaluated and compared by recent benchmarkin...

Full description

Saved in:
Bibliographic Details
Main Authors: Qingxia LIU, Junyou LI, Gong CHENG
Format: Article
Language:zho
Published: China InfoCom Media Group 2021-05-01
Series:大数据
Subjects:
Online Access:http://www.j-bigdataresearch.com.cn/thesisDetails#10.11959/j.issn.2096-0271.2021023
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850212455302561792
author Qingxia LIU
Junyou LI
Gong CHENG
author_facet Qingxia LIU
Junyou LI
Gong CHENG
author_sort Qingxia LIU
collection DOAJ
description The task of entity summarization (ES) is to select an optimum subset from a large set of triples describing an entity in a knowledge graph.ES systems often integrate many and various ES features in a complex way.While state-of-the-art ES systems have been evaluated and compared by recent benchmarking efforts, it was unclear whether and how much each constituent ES feature had contributed to the performance of an ES system.An interpretive evaluation of ES systems was proposed.Two novel evaluation metrics were proposed, feature effectiveness ratio and feature significance ratio, to characterize how much ground-truth summaries and machine-generated summaries exhibit each ES feature.Their comparison would help to interpret the performance of an ES system.Based on three benchmarks, metrics with six popular ES features were implemented, and an interpretive evaluation of nine unsupervised ES systems and two supervised ES systems were presented.The code and data are open source.
format Article
id doaj-art-4fdda210826e446bba55b5e7a6ea199b
institution OA Journals
issn 2096-0271
language zho
publishDate 2021-05-01
publisher China InfoCom Media Group
record_format Article
series 大数据
spelling doaj-art-4fdda210826e446bba55b5e7a6ea199b2025-08-20T02:09:21ZzhoChina InfoCom Media Group大数据2096-02712021-05-017202102359537830An interpretive evaluation of entity summarization systemQingxia LIUJunyou LIGong CHENGThe task of entity summarization (ES) is to select an optimum subset from a large set of triples describing an entity in a knowledge graph.ES systems often integrate many and various ES features in a complex way.While state-of-the-art ES systems have been evaluated and compared by recent benchmarking efforts, it was unclear whether and how much each constituent ES feature had contributed to the performance of an ES system.An interpretive evaluation of ES systems was proposed.Two novel evaluation metrics were proposed, feature effectiveness ratio and feature significance ratio, to characterize how much ground-truth summaries and machine-generated summaries exhibit each ES feature.Their comparison would help to interpret the performance of an ES system.Based on three benchmarks, metrics with six popular ES features were implemented, and an interpretive evaluation of nine unsupervised ES systems and two supervised ES systems were presented.The code and data are open source.http://www.j-bigdataresearch.com.cn/thesisDetails#10.11959/j.issn.2096-0271.2021023knowledge graph;entity summarization;benchmark
spellingShingle Qingxia LIU
Junyou LI
Gong CHENG
An interpretive evaluation of entity summarization system
大数据
knowledge graph;entity summarization;benchmark
title An interpretive evaluation of entity summarization system
title_full An interpretive evaluation of entity summarization system
title_fullStr An interpretive evaluation of entity summarization system
title_full_unstemmed An interpretive evaluation of entity summarization system
title_short An interpretive evaluation of entity summarization system
title_sort interpretive evaluation of entity summarization system
topic knowledge graph;entity summarization;benchmark
url http://www.j-bigdataresearch.com.cn/thesisDetails#10.11959/j.issn.2096-0271.2021023
work_keys_str_mv AT qingxialiu aninterpretiveevaluationofentitysummarizationsystem
AT junyouli aninterpretiveevaluationofentitysummarizationsystem
AT gongcheng aninterpretiveevaluationofentitysummarizationsystem
AT qingxialiu interpretiveevaluationofentitysummarizationsystem
AT junyouli interpretiveevaluationofentitysummarizationsystem
AT gongcheng interpretiveevaluationofentitysummarizationsystem