@inproceedings{busemann-zhang-2008-identifying,
title = "Identifying Foreign Person Names in {C}hinese Text",
author = "Busemann, Stephan and
Zhang, Yajing",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/635_paper.pdf",
abstract = "Foreign name expressions written in Chinese characters are difficult to recognize since the sequence of characters represents the Chinese pronunciation of the name. This paper suggests that known English or German person names can reliably be identified on the basis of the similarity between the Chinese and the foreign pronunciation. In addition to locating a person name in the text and learning that it is foreign, the corresponding foreign name is identified, thus gaining precious additional information for cross-lingual applications. This idea is implemented as a statistical module into the rule-based shallow parsing system SProUT, forming the HyFex system. The statistical component is invoked if a sequence of trigger characters is found that may correspond to a foreign name. Their phonetic Pinyin representation is produced and compared to the phonetic representations (SAMPA) of given foreign names, which are generated by the MARY TTS system for German and English pronunciations. This comparison is achieved by a hand-crafted metric that assigns costs to specific edit operations. The person name corresponding to the SAMPA representation with the lowest costs attached is returned as the most similar result, if a threshold is not exceeded. Our evaluation on publicly available data shows competitive results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="busemann-zhang-2008-identifying">
<titleInfo>
<title>Identifying Foreign Person Names in Chinese Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stephan</namePart>
<namePart type="family">Busemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yajing</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Foreign name expressions written in Chinese characters are difficult to recognize since the sequence of characters represents the Chinese pronunciation of the name. This paper suggests that known English or German person names can reliably be identified on the basis of the similarity between the Chinese and the foreign pronunciation. In addition to locating a person name in the text and learning that it is foreign, the corresponding foreign name is identified, thus gaining precious additional information for cross-lingual applications. This idea is implemented as a statistical module into the rule-based shallow parsing system SProUT, forming the HyFex system. The statistical component is invoked if a sequence of trigger characters is found that may correspond to a foreign name. Their phonetic Pinyin representation is produced and compared to the phonetic representations (SAMPA) of given foreign names, which are generated by the MARY TTS system for German and English pronunciations. This comparison is achieved by a hand-crafted metric that assigns costs to specific edit operations. The person name corresponding to the SAMPA representation with the lowest costs attached is returned as the most similar result, if a threshold is not exceeded. Our evaluation on publicly available data shows competitive results.</abstract>
<identifier type="citekey">busemann-zhang-2008-identifying</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/635_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Identifying Foreign Person Names in Chinese Text
%A Busemann, Stephan
%A Zhang, Yajing
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F busemann-zhang-2008-identifying
%X Foreign name expressions written in Chinese characters are difficult to recognize since the sequence of characters represents the Chinese pronunciation of the name. This paper suggests that known English or German person names can reliably be identified on the basis of the similarity between the Chinese and the foreign pronunciation. In addition to locating a person name in the text and learning that it is foreign, the corresponding foreign name is identified, thus gaining precious additional information for cross-lingual applications. This idea is implemented as a statistical module into the rule-based shallow parsing system SProUT, forming the HyFex system. The statistical component is invoked if a sequence of trigger characters is found that may correspond to a foreign name. Their phonetic Pinyin representation is produced and compared to the phonetic representations (SAMPA) of given foreign names, which are generated by the MARY TTS system for German and English pronunciations. This comparison is achieved by a hand-crafted metric that assigns costs to specific edit operations. The person name corresponding to the SAMPA representation with the lowest costs attached is returned as the most similar result, if a threshold is not exceeded. Our evaluation on publicly available data shows competitive results.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/635_paper.pdf
Markdown (Informal)
[Identifying Foreign Person Names in Chinese Text](http://www.lrec-conf.org/proceedings/lrec2008/pdf/635_paper.pdf) (Busemann & Zhang, LREC 2008)
ACL
- Stephan Busemann and Yajing Zhang. 2008. Identifying Foreign Person Names in Chinese Text. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).