Community relation discovery by named entities

Jianhan Zhu, Alexandre L. Gonçalves, Victoria S. Uren, Enrico Motta, Roberto Pacheco, Dawei Song, Stefan Rüger

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Discovering who works with whom, on which projects and with which customers is a key task in knowledge management. Although most organizations keep models of organizational structures, these models do not necessarily accurately reflect the reality on the ground. In this paper we present a text mining method called CORDER which first recognizes named entities (NEs) of various types from Web pages, and then discovers relations from a target NE to other NEs which co-occur with it. We evaluated the method on our departmental Website. We used the CORDER method to first find related NEs of four types (organizations, people, projects, and research areas) from Web pages on the Website and then rank them according to their co-occurrence with each of the people in our department. 20 representative people were selected and each of them was presented with ranked lists of each type of NE. Each person specified whether these NEs were related to him/her and changed or confirmed their rankings. Our results indicate that the method can find the NEs with which these people are closely related and provide accurate rankings.
Original languageEnglish
Title of host publicationProceedings of the sixth International Conference on Machine Learning and Cybernetics, Hong Kong, 19-22 August 2007
PublisherIEEE
Pages1966-1973
Number of pages8
ISBN (Electronic)978-1-4244-0973-0
DOIs
Publication statusPublished - 2007
Event6th International Conference on Machine Learning and Cybernetics - Hong Kong, China
Duration: 19 Aug 200722 Aug 2007

Conference

Conference6th International Conference on Machine Learning and Cybernetics
CountryChina
CityHong Kong
Period19/08/0722/08/07

Fingerprint

Websites
Knowledge management
Model structures

Keywords

  • relation discovery
  • ranking
  • similarities
  • named entity recognition
  • clustering

Cite this

Zhu, J., Gonçalves, A. L., Uren, V. S., Motta, E., Pacheco, R., Song, D., & Rüger, S. (2007). Community relation discovery by named entities. In Proceedings of the sixth International Conference on Machine Learning and Cybernetics, Hong Kong, 19-22 August 2007 (pp. 1966-1973). IEEE. https://doi.org/10.1109/ICMLC.2007.4370469
Zhu, Jianhan ; Gonçalves, Alexandre L. ; Uren, Victoria S. ; Motta, Enrico ; Pacheco, Roberto ; Song, Dawei ; Rüger, Stefan. / Community relation discovery by named entities. Proceedings of the sixth International Conference on Machine Learning and Cybernetics, Hong Kong, 19-22 August 2007. IEEE, 2007. pp. 1966-1973
@inproceedings{be6f1fc7f4da4970b701c269dc228df3,
title = "Community relation discovery by named entities",
abstract = "Discovering who works with whom, on which projects and with which customers is a key task in knowledge management. Although most organizations keep models of organizational structures, these models do not necessarily accurately reflect the reality on the ground. In this paper we present a text mining method called CORDER which first recognizes named entities (NEs) of various types from Web pages, and then discovers relations from a target NE to other NEs which co-occur with it. We evaluated the method on our departmental Website. We used the CORDER method to first find related NEs of four types (organizations, people, projects, and research areas) from Web pages on the Website and then rank them according to their co-occurrence with each of the people in our department. 20 representative people were selected and each of them was presented with ranked lists of each type of NE. Each person specified whether these NEs were related to him/her and changed or confirmed their rankings. Our results indicate that the method can find the NEs with which these people are closely related and provide accurate rankings.",
keywords = "relation discovery, ranking, similarities, named entity recognition, clustering",
author = "Jianhan Zhu and Gon{\cc}alves, {Alexandre L.} and Uren, {Victoria S.} and Enrico Motta and Roberto Pacheco and Dawei Song and Stefan R{\"u}ger",
year = "2007",
doi = "10.1109/ICMLC.2007.4370469",
language = "English",
pages = "1966--1973",
booktitle = "Proceedings of the sixth International Conference on Machine Learning and Cybernetics, Hong Kong, 19-22 August 2007",
publisher = "IEEE",
address = "United States",

}

Zhu, J, Gonçalves, AL, Uren, VS, Motta, E, Pacheco, R, Song, D & Rüger, S 2007, Community relation discovery by named entities. in Proceedings of the sixth International Conference on Machine Learning and Cybernetics, Hong Kong, 19-22 August 2007. IEEE, pp. 1966-1973, 6th International Conference on Machine Learning and Cybernetics, Hong Kong, China, 19/08/07. https://doi.org/10.1109/ICMLC.2007.4370469

Community relation discovery by named entities. / Zhu, Jianhan; Gonçalves, Alexandre L.; Uren, Victoria S.; Motta, Enrico; Pacheco, Roberto ; Song, Dawei; Rüger, Stefan.

Proceedings of the sixth International Conference on Machine Learning and Cybernetics, Hong Kong, 19-22 August 2007. IEEE, 2007. p. 1966-1973.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Community relation discovery by named entities

AU - Zhu, Jianhan

AU - Gonçalves, Alexandre L.

AU - Uren, Victoria S.

AU - Motta, Enrico

AU - Pacheco, Roberto

AU - Song, Dawei

AU - Rüger, Stefan

PY - 2007

Y1 - 2007

N2 - Discovering who works with whom, on which projects and with which customers is a key task in knowledge management. Although most organizations keep models of organizational structures, these models do not necessarily accurately reflect the reality on the ground. In this paper we present a text mining method called CORDER which first recognizes named entities (NEs) of various types from Web pages, and then discovers relations from a target NE to other NEs which co-occur with it. We evaluated the method on our departmental Website. We used the CORDER method to first find related NEs of four types (organizations, people, projects, and research areas) from Web pages on the Website and then rank them according to their co-occurrence with each of the people in our department. 20 representative people were selected and each of them was presented with ranked lists of each type of NE. Each person specified whether these NEs were related to him/her and changed or confirmed their rankings. Our results indicate that the method can find the NEs with which these people are closely related and provide accurate rankings.

AB - Discovering who works with whom, on which projects and with which customers is a key task in knowledge management. Although most organizations keep models of organizational structures, these models do not necessarily accurately reflect the reality on the ground. In this paper we present a text mining method called CORDER which first recognizes named entities (NEs) of various types from Web pages, and then discovers relations from a target NE to other NEs which co-occur with it. We evaluated the method on our departmental Website. We used the CORDER method to first find related NEs of four types (organizations, people, projects, and research areas) from Web pages on the Website and then rank them according to their co-occurrence with each of the people in our department. 20 representative people were selected and each of them was presented with ranked lists of each type of NE. Each person specified whether these NEs were related to him/her and changed or confirmed their rankings. Our results indicate that the method can find the NEs with which these people are closely related and provide accurate rankings.

KW - relation discovery

KW - ranking

KW - similarities

KW - named entity recognition

KW - clustering

UR - http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=4370469

U2 - 10.1109/ICMLC.2007.4370469

DO - 10.1109/ICMLC.2007.4370469

M3 - Conference contribution

SP - 1966

EP - 1973

BT - Proceedings of the sixth International Conference on Machine Learning and Cybernetics, Hong Kong, 19-22 August 2007

PB - IEEE

ER -

Zhu J, Gonçalves AL, Uren VS, Motta E, Pacheco R, Song D et al. Community relation discovery by named entities. In Proceedings of the sixth International Conference on Machine Learning and Cybernetics, Hong Kong, 19-22 August 2007. IEEE. 2007. p. 1966-1973 https://doi.org/10.1109/ICMLC.2007.4370469