MAGES: A Multilingual Angle-integrated Grouping-based Entity Summarization System

Eun-kyung Kim, Key-Sun Choi


Abstract
This demo presents MAGES (multilingual angle-integrated grouping-based entity summarization), an entity summarization system for a large knowledge base such as DBpedia based on a entity-group-bound ranking in a single integrated entity space across multiple language-specific editions. MAGES offers a multilingual angle-integrated space model, which has the advantage of overcoming missing semantic tags (i.e., categories) caused by biases in different language communities, and can contribute to the creation of entity groups that are well-formed and more stable than the monolingual condition within it. MAGES can help people quickly identify the essential points of the entities when they search or browse a large volume of entity-centric data. Evaluation results on the same experimental data demonstrate that our system produces a better summary compared with other representative DBpedia entity summarization methods.
Anthology ID:
C16-2043
Volume:
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: System Demonstrations
Month:
December
Year:
2016
Address:
Osaka, Japan
Editor:
Hideo Watanabe
Venue:
COLING
SIG:
Publisher:
The COLING 2016 Organizing Committee
Note:
Pages:
203–207
Language:
URL:
https://aclanthology.org/C16-2043
DOI:
Bibkey:
Cite (ACL):
Eun-kyung Kim and Key-Sun Choi. 2016. MAGES: A Multilingual Angle-integrated Grouping-based Entity Summarization System. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: System Demonstrations, pages 203–207, Osaka, Japan. The COLING 2016 Organizing Committee.
Cite (Informal):
MAGES: A Multilingual Angle-integrated Grouping-based Entity Summarization System (Kim & Choi, COLING 2016)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/C16-2043.pdf