Mining entity translations from comparable corpora: A holistic graph mapping approach

Jinhan Kim, Long Jiang, Seung Won Hwang, Young In Song, Ming Zhou

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

11 Citations (Scopus)

Abstract

This paper addresses the problem of mining named entity translations from comparable corpora, specifically, mining English and Chinese named entity translation. We first observe that existing approaches use one or more of the following named entity similarity metrics: entity, entity context, and relationship. Inspired by this observation, in this paper, we propose a new holistic approach, by (1) combining all similarity types used and (2) additionally considering relationship context similarity between pairs of named entities, a missing quadrant in the taxonomy of similarity metrics. We abstract the named entity translation problem as the matching of two named entity graphs extracted from the comparable corpora. Specifically, named entity graphs are first constructed from comparable corpora to extract relationship between named entities. Entity similarity and entity context similarity are then calculated from every pair of bilingual named entities. A reinforcing method is utilized to reflect relationship similarity and relationship context similarity between named entities. According to our experimental results, our holistic graph-based approach significantly outperforms previous approaches.

Original languageEnglish
Title of host publicationCIKM'11 - Proceedings of the 2011 ACM International Conference on Information and Knowledge Management
Pages1295-1304
Number of pages10
DOIs
Publication statusPublished - 2011 Dec 13
Event20th ACM Conference on Information and Knowledge Management, CIKM'11 - Glasgow, United Kingdom
Duration: 2011 Oct 242011 Oct 28

Publication series

NameInternational Conference on Information and Knowledge Management, Proceedings

Other

Other20th ACM Conference on Information and Knowledge Management, CIKM'11
CountryUnited Kingdom
CityGlasgow
Period11/10/2411/10/28

Fingerprint

Named entity
Graph
Holistic approach
Taxonomy

All Science Journal Classification (ASJC) codes

  • Decision Sciences(all)
  • Business, Management and Accounting(all)

Cite this

Kim, J., Jiang, L., Hwang, S. W., Song, Y. I., & Zhou, M. (2011). Mining entity translations from comparable corpora: A holistic graph mapping approach. In CIKM'11 - Proceedings of the 2011 ACM International Conference on Information and Knowledge Management (pp. 1295-1304). (International Conference on Information and Knowledge Management, Proceedings). https://doi.org/10.1145/2063576.2063764
Kim, Jinhan ; Jiang, Long ; Hwang, Seung Won ; Song, Young In ; Zhou, Ming. / Mining entity translations from comparable corpora : A holistic graph mapping approach. CIKM'11 - Proceedings of the 2011 ACM International Conference on Information and Knowledge Management. 2011. pp. 1295-1304 (International Conference on Information and Knowledge Management, Proceedings).
@inproceedings{6c82ffda42434338b12aed4ad6e524db,
title = "Mining entity translations from comparable corpora: A holistic graph mapping approach",
abstract = "This paper addresses the problem of mining named entity translations from comparable corpora, specifically, mining English and Chinese named entity translation. We first observe that existing approaches use one or more of the following named entity similarity metrics: entity, entity context, and relationship. Inspired by this observation, in this paper, we propose a new holistic approach, by (1) combining all similarity types used and (2) additionally considering relationship context similarity between pairs of named entities, a missing quadrant in the taxonomy of similarity metrics. We abstract the named entity translation problem as the matching of two named entity graphs extracted from the comparable corpora. Specifically, named entity graphs are first constructed from comparable corpora to extract relationship between named entities. Entity similarity and entity context similarity are then calculated from every pair of bilingual named entities. A reinforcing method is utilized to reflect relationship similarity and relationship context similarity between named entities. According to our experimental results, our holistic graph-based approach significantly outperforms previous approaches.",
author = "Jinhan Kim and Long Jiang and Hwang, {Seung Won} and Song, {Young In} and Ming Zhou",
year = "2011",
month = "12",
day = "13",
doi = "10.1145/2063576.2063764",
language = "English",
isbn = "9781450307178",
series = "International Conference on Information and Knowledge Management, Proceedings",
pages = "1295--1304",
booktitle = "CIKM'11 - Proceedings of the 2011 ACM International Conference on Information and Knowledge Management",

}

Kim, J, Jiang, L, Hwang, SW, Song, YI & Zhou, M 2011, Mining entity translations from comparable corpora: A holistic graph mapping approach. in CIKM'11 - Proceedings of the 2011 ACM International Conference on Information and Knowledge Management. International Conference on Information and Knowledge Management, Proceedings, pp. 1295-1304, 20th ACM Conference on Information and Knowledge Management, CIKM'11, Glasgow, United Kingdom, 11/10/24. https://doi.org/10.1145/2063576.2063764

Mining entity translations from comparable corpora : A holistic graph mapping approach. / Kim, Jinhan; Jiang, Long; Hwang, Seung Won; Song, Young In; Zhou, Ming.

CIKM'11 - Proceedings of the 2011 ACM International Conference on Information and Knowledge Management. 2011. p. 1295-1304 (International Conference on Information and Knowledge Management, Proceedings).

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

TY - GEN

T1 - Mining entity translations from comparable corpora

T2 - A holistic graph mapping approach

AU - Kim, Jinhan

AU - Jiang, Long

AU - Hwang, Seung Won

AU - Song, Young In

AU - Zhou, Ming

PY - 2011/12/13

Y1 - 2011/12/13

N2 - This paper addresses the problem of mining named entity translations from comparable corpora, specifically, mining English and Chinese named entity translation. We first observe that existing approaches use one or more of the following named entity similarity metrics: entity, entity context, and relationship. Inspired by this observation, in this paper, we propose a new holistic approach, by (1) combining all similarity types used and (2) additionally considering relationship context similarity between pairs of named entities, a missing quadrant in the taxonomy of similarity metrics. We abstract the named entity translation problem as the matching of two named entity graphs extracted from the comparable corpora. Specifically, named entity graphs are first constructed from comparable corpora to extract relationship between named entities. Entity similarity and entity context similarity are then calculated from every pair of bilingual named entities. A reinforcing method is utilized to reflect relationship similarity and relationship context similarity between named entities. According to our experimental results, our holistic graph-based approach significantly outperforms previous approaches.

AB - This paper addresses the problem of mining named entity translations from comparable corpora, specifically, mining English and Chinese named entity translation. We first observe that existing approaches use one or more of the following named entity similarity metrics: entity, entity context, and relationship. Inspired by this observation, in this paper, we propose a new holistic approach, by (1) combining all similarity types used and (2) additionally considering relationship context similarity between pairs of named entities, a missing quadrant in the taxonomy of similarity metrics. We abstract the named entity translation problem as the matching of two named entity graphs extracted from the comparable corpora. Specifically, named entity graphs are first constructed from comparable corpora to extract relationship between named entities. Entity similarity and entity context similarity are then calculated from every pair of bilingual named entities. A reinforcing method is utilized to reflect relationship similarity and relationship context similarity between named entities. According to our experimental results, our holistic graph-based approach significantly outperforms previous approaches.

UR - http://www.scopus.com/inward/record.url?scp=83055179414&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=83055179414&partnerID=8YFLogxK

U2 - 10.1145/2063576.2063764

DO - 10.1145/2063576.2063764

M3 - Conference contribution

AN - SCOPUS:83055179414

SN - 9781450307178

T3 - International Conference on Information and Knowledge Management, Proceedings

SP - 1295

EP - 1304

BT - CIKM'11 - Proceedings of the 2011 ACM International Conference on Information and Knowledge Management

ER -

Kim J, Jiang L, Hwang SW, Song YI, Zhou M. Mining entity translations from comparable corpora: A holistic graph mapping approach. In CIKM'11 - Proceedings of the 2011 ACM International Conference on Information and Knowledge Management. 2011. p. 1295-1304. (International Conference on Information and Knowledge Management, Proceedings). https://doi.org/10.1145/2063576.2063764