The effects of high quality translations of named entities in cross-language information exploration

Dan Wu, Daqing He, Heng Ji, Ralph Grishman

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

Abstract

Named entities (NEs) are the expressions in human languages that explicitly link notations in languages to the entities in the real world. They play important role in cross-language information retrieval (CLIR) because most users' requests have been found to have NEs, and majority of out-of-vocabulary terms are NEs. Therefore, missing their translations has a significant impact to the retrieval effectiveness. In this paper, we examined the effect of high quality translations of NEs in event driven information exploration, where the existence of NEs is even more common. With the focus on the effect of NE translations obtained by using information extraction (IE) techniques, we conducted several experiments using TDT test collections. Our results demonstrate that NEs and their translations play critical roles in improving CLIR effectiveness, and it makes positive impact in CLIR to use high quality translations of NEs obtained by IE techniques.

Original languageEnglish (US)
Title of host publication2008 International Conference on Natural Language Processing and Knowledge Engineering, NLP-KE 2008
DOIs
StatePublished - 2008
Event2008 International Conference on Natural Language Processing and Knowledge Engineering, NLP-KE 2008 - Beijing, China
Duration: Oct 19 2008Oct 22 2008

Other

Other2008 International Conference on Natural Language Processing and Knowledge Engineering, NLP-KE 2008
CountryChina
CityBeijing
Period10/19/0810/22/08

Fingerprint

Query languages
Experiments

Keywords

  • Cross-language information exploration
  • Named entity

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software

Cite this

Wu, D., He, D., Ji, H., & Grishman, R. (2008). The effects of high quality translations of named entities in cross-language information exploration. In 2008 International Conference on Natural Language Processing and Knowledge Engineering, NLP-KE 2008 [4906770] https://doi.org/10.1109/NLPKE.2008.4906770

The effects of high quality translations of named entities in cross-language information exploration. / Wu, Dan; He, Daqing; Ji, Heng; Grishman, Ralph.

2008 International Conference on Natural Language Processing and Knowledge Engineering, NLP-KE 2008. 2008. 4906770.

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

Wu, D, He, D, Ji, H & Grishman, R 2008, The effects of high quality translations of named entities in cross-language information exploration. in 2008 International Conference on Natural Language Processing and Knowledge Engineering, NLP-KE 2008., 4906770, 2008 International Conference on Natural Language Processing and Knowledge Engineering, NLP-KE 2008, Beijing, China, 10/19/08. https://doi.org/10.1109/NLPKE.2008.4906770
Wu D, He D, Ji H, Grishman R. The effects of high quality translations of named entities in cross-language information exploration. In 2008 International Conference on Natural Language Processing and Knowledge Engineering, NLP-KE 2008. 2008. 4906770 https://doi.org/10.1109/NLPKE.2008.4906770
Wu, Dan ; He, Daqing ; Ji, Heng ; Grishman, Ralph. / The effects of high quality translations of named entities in cross-language information exploration. 2008 International Conference on Natural Language Processing and Knowledge Engineering, NLP-KE 2008. 2008.
@inproceedings{50c8b01b1ed54dacaddad2601244893a,
title = "The effects of high quality translations of named entities in cross-language information exploration",
abstract = "Named entities (NEs) are the expressions in human languages that explicitly link notations in languages to the entities in the real world. They play important role in cross-language information retrieval (CLIR) because most users' requests have been found to have NEs, and majority of out-of-vocabulary terms are NEs. Therefore, missing their translations has a significant impact to the retrieval effectiveness. In this paper, we examined the effect of high quality translations of NEs in event driven information exploration, where the existence of NEs is even more common. With the focus on the effect of NE translations obtained by using information extraction (IE) techniques, we conducted several experiments using TDT test collections. Our results demonstrate that NEs and their translations play critical roles in improving CLIR effectiveness, and it makes positive impact in CLIR to use high quality translations of NEs obtained by IE techniques.",
keywords = "Cross-language information exploration, Named entity",
author = "Dan Wu and Daqing He and Heng Ji and Ralph Grishman",
year = "2008",
doi = "10.1109/NLPKE.2008.4906770",
language = "English (US)",
isbn = "9781424427802",
booktitle = "2008 International Conference on Natural Language Processing and Knowledge Engineering, NLP-KE 2008",

}

TY - GEN

T1 - The effects of high quality translations of named entities in cross-language information exploration

AU - Wu, Dan

AU - He, Daqing

AU - Ji, Heng

AU - Grishman, Ralph

PY - 2008

Y1 - 2008

N2 - Named entities (NEs) are the expressions in human languages that explicitly link notations in languages to the entities in the real world. They play important role in cross-language information retrieval (CLIR) because most users' requests have been found to have NEs, and majority of out-of-vocabulary terms are NEs. Therefore, missing their translations has a significant impact to the retrieval effectiveness. In this paper, we examined the effect of high quality translations of NEs in event driven information exploration, where the existence of NEs is even more common. With the focus on the effect of NE translations obtained by using information extraction (IE) techniques, we conducted several experiments using TDT test collections. Our results demonstrate that NEs and their translations play critical roles in improving CLIR effectiveness, and it makes positive impact in CLIR to use high quality translations of NEs obtained by IE techniques.

AB - Named entities (NEs) are the expressions in human languages that explicitly link notations in languages to the entities in the real world. They play important role in cross-language information retrieval (CLIR) because most users' requests have been found to have NEs, and majority of out-of-vocabulary terms are NEs. Therefore, missing their translations has a significant impact to the retrieval effectiveness. In this paper, we examined the effect of high quality translations of NEs in event driven information exploration, where the existence of NEs is even more common. With the focus on the effect of NE translations obtained by using information extraction (IE) techniques, we conducted several experiments using TDT test collections. Our results demonstrate that NEs and their translations play critical roles in improving CLIR effectiveness, and it makes positive impact in CLIR to use high quality translations of NEs obtained by IE techniques.

KW - Cross-language information exploration

KW - Named entity

UR - http://www.scopus.com/inward/record.url?scp=67650360388&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67650360388&partnerID=8YFLogxK

U2 - 10.1109/NLPKE.2008.4906770

DO - 10.1109/NLPKE.2008.4906770

M3 - Conference contribution

SN - 9781424427802

BT - 2008 International Conference on Natural Language Processing and Knowledge Engineering, NLP-KE 2008

ER -