Translating-Transliterating Named Entities for Multilingual Information Access
H. Chen, W. Lin, C. Yang, and W. Lin. Journal of the American Society for Information Science and Technology, (2006)
Abstract
Named entities are major constituents of a document but are usually unknown words. This work proposes a systematic way of dealing with formulation, transformation, translation, and transliteration of multilingual-named entities. The rules and similarity matrices for translation and transliteration are learned automatically from parallel-named-entity corpora. The results are applied in cross-language access to collections of images with captions. Experimental results demonstrate that the similarity-based transliteration of named entities is effective, and runs in which transliteration is considered outperform the runs in which it is neglected.
%0 Journal Article
%1 Chen2006
%A Chen, H H
%A Lin, W C
%A Yang, C H
%A Lin, W H
%D 2006
%J Journal of the American Society for Information Science and Technology
%K Acceso a informaci{\'{o}}n,Entidades,Multiculturalismo,Multiling{\"{u}}ismo,Traducci{\'{o}}n la
%N 5
%T Translating-Transliterating Named Entities for Multilingual Information Access
%U http://www3.interscience.wiley.com/cgi-bin/jtoc/76501873/
%V 57
%X Named entities are major constituents of a document but are usually unknown words. This work proposes a systematic way of dealing with formulation, transformation, translation, and transliteration of multilingual-named entities. The rules and similarity matrices for translation and transliteration are learned automatically from parallel-named-entity corpora. The results are applied in cross-language access to collections of images with captions. Experimental results demonstrate that the similarity-based transliteration of named entities is effective, and runs in which transliteration is considered outperform the runs in which it is neglected.
%Z Language: eng
@article{Chen2006,
abstract = {Named entities are major constituents of a document but are usually unknown words. This work proposes a systematic way of dealing with formulation, transformation, translation, and transliteration of multilingual-named entities. The rules and similarity matrices for translation and transliteration are learned automatically from parallel-named-entity corpora. The results are applied in cross-language access to collections of images with captions. Experimental results demonstrate that the similarity-based transliteration of named entities is effective, and runs in which transliteration is considered outperform the runs in which it is neglected.},
added-at = {2015-12-01T11:33:23.000+0100},
annote = {Language: eng},
author = {Chen, H H and Lin, W C and Yang, C H and Lin, W H},
biburl = {https://www.bibsonomy.org/bibtex/2960c85d5a8afdeecec365a9778713d96/sofiagruiz92},
interhash = {709c97747baa1bd9e45fb342659e1f87},
intrahash = {960c85d5a8afdeecec365a9778713d96},
journal = {Journal of the American Society for Information Science and Technology},
keywords = {Acceso a informaci{\'{o}}n,Entidades,Multiculturalismo,Multiling{\"{u}}ismo,Traducci{\'{o}}n la},
number = 5,
timestamp = {2015-12-01T11:33:23.000+0100},
title = {{Translating-Transliterating Named Entities for Multilingual Information Access}},
url = {http://www3.interscience.wiley.com/cgi-bin/jtoc/76501873/},
volume = 57,
year = 2006
}