Entity descriptions have been exponentially growing in community-generated knowledge databases, such as DBpedia. However, many of those descriptions are not useful for identifying the underlying characteristics of their corresponding entities because semantically redundant facts or triples are included in the descriptions that represent the connections between entities without any semantic properties. Entity summarization is applied to filter out such non-informative triples and meaning-redundant triples and rank the remaining informative facts within the size of the triples for summarization. This study proposes an entity summarization approach based on pre-grouping the entities that share a set of attributes that can be used to characterize the entities we want to summarize. Entities are first grouped according to projected multilingual categories that provide the multi-angled semantics of each entity into a single entity space. Key facts about the entity are then determined through in-group-based rankings. As a result, our proposed approach produced summary information of significantly better quality (p-value =1.52×10-3 and 2.01×10-3 for the top-10 and -5 summaries, respectively) than the state-of-the-art method that requires additional external resources.
Eun-kyung KIM
Korea Advanced Institute of Science and Technology (KAIST)
Key-Sun CHOI
Korea Advanced Institute of Science and Technology (KAIST)
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Eun-kyung KIM, Key-Sun CHOI, "Entity Summarization Based on Entity Grouping in Multilingual Projected Entity Space" in IEICE TRANSACTIONS on Information,
vol. E100-D, no. 9, pp. 2138-2146, September 2017, doi: 10.1587/transinf.2016EDP7235.
Abstract: Entity descriptions have been exponentially growing in community-generated knowledge databases, such as DBpedia. However, many of those descriptions are not useful for identifying the underlying characteristics of their corresponding entities because semantically redundant facts or triples are included in the descriptions that represent the connections between entities without any semantic properties. Entity summarization is applied to filter out such non-informative triples and meaning-redundant triples and rank the remaining informative facts within the size of the triples for summarization. This study proposes an entity summarization approach based on pre-grouping the entities that share a set of attributes that can be used to characterize the entities we want to summarize. Entities are first grouped according to projected multilingual categories that provide the multi-angled semantics of each entity into a single entity space. Key facts about the entity are then determined through in-group-based rankings. As a result, our proposed approach produced summary information of significantly better quality (p-value =1.52×10-3 and 2.01×10-3 for the top-10 and -5 summaries, respectively) than the state-of-the-art method that requires additional external resources.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2016EDP7235/_p
Copy
@ARTICLE{e100-d_9_2138,
author={Eun-kyung KIM, Key-Sun CHOI, },
journal={IEICE TRANSACTIONS on Information},
title={Entity Summarization Based on Entity Grouping in Multilingual Projected Entity Space},
year={2017},
volume={E100-D},
number={9},
pages={2138-2146},
abstract={Entity descriptions have been exponentially growing in community-generated knowledge databases, such as DBpedia. However, many of those descriptions are not useful for identifying the underlying characteristics of their corresponding entities because semantically redundant facts or triples are included in the descriptions that represent the connections between entities without any semantic properties. Entity summarization is applied to filter out such non-informative triples and meaning-redundant triples and rank the remaining informative facts within the size of the triples for summarization. This study proposes an entity summarization approach based on pre-grouping the entities that share a set of attributes that can be used to characterize the entities we want to summarize. Entities are first grouped according to projected multilingual categories that provide the multi-angled semantics of each entity into a single entity space. Key facts about the entity are then determined through in-group-based rankings. As a result, our proposed approach produced summary information of significantly better quality (p-value =1.52×10-3 and 2.01×10-3 for the top-10 and -5 summaries, respectively) than the state-of-the-art method that requires additional external resources.},
keywords={},
doi={10.1587/transinf.2016EDP7235},
ISSN={1745-1361},
month={September},}
Copy
TY - JOUR
TI - Entity Summarization Based on Entity Grouping in Multilingual Projected Entity Space
T2 - IEICE TRANSACTIONS on Information
SP - 2138
EP - 2146
AU - Eun-kyung KIM
AU - Key-Sun CHOI
PY - 2017
DO - 10.1587/transinf.2016EDP7235
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E100-D
IS - 9
JA - IEICE TRANSACTIONS on Information
Y1 - September 2017
AB - Entity descriptions have been exponentially growing in community-generated knowledge databases, such as DBpedia. However, many of those descriptions are not useful for identifying the underlying characteristics of their corresponding entities because semantically redundant facts or triples are included in the descriptions that represent the connections between entities without any semantic properties. Entity summarization is applied to filter out such non-informative triples and meaning-redundant triples and rank the remaining informative facts within the size of the triples for summarization. This study proposes an entity summarization approach based on pre-grouping the entities that share a set of attributes that can be used to characterize the entities we want to summarize. Entities are first grouped according to projected multilingual categories that provide the multi-angled semantics of each entity into a single entity space. Key facts about the entity are then determined through in-group-based rankings. As a result, our proposed approach produced summary information of significantly better quality (p-value =1.52×10-3 and 2.01×10-3 for the top-10 and -5 summaries, respectively) than the state-of-the-art method that requires additional external resources.
ER -