@inproceedings{mota-grishman-2008-ne,
title = "Is this {NE} tagger getting old?",
author = "Mota, Cristina and
Grishman, Ralph",
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/303_paper.pdf",
abstract = "This paper focuses on the influence of changing the text time frame on the performance of a named entity tagger. We followed a twofold approach to investigate this subject: on the one hand, we analyzed a corpus that spans 8 years, and, on the other hand, we assessed the performance of a name tagger trained and tested on that corpus. We created 8 samples from the corpus, each drawn from the articles for a particular year. In terms of corpus analysis, we calculated the corpus similarity and names shared between samples. To see the effect on tagger performance, we implemented a semi-supervised name tagger based on co-training; then, we trained and tested our tagger on those samples. We observed that corpus similarity, names shared between samples, and tagger performance all decay as the time gap between the samples increases. Furthermore, we observed that the corpus similarity and names shared correlate with the tagger F-measure. These results show that named entity recognition systems may become obsolete in a short period of time.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mota-grishman-2008-ne">
<titleInfo>
<title>Is this NE tagger getting old?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cristina</namePart>
<namePart type="family">Mota</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ralph</namePart>
<namePart type="family">Grishman</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>This paper focuses on the influence of changing the text time frame on the performance of a named entity tagger. We followed a twofold approach to investigate this subject: on the one hand, we analyzed a corpus that spans 8 years, and, on the other hand, we assessed the performance of a name tagger trained and tested on that corpus. We created 8 samples from the corpus, each drawn from the articles for a particular year. In terms of corpus analysis, we calculated the corpus similarity and names shared between samples. To see the effect on tagger performance, we implemented a semi-supervised name tagger based on co-training; then, we trained and tested our tagger on those samples. We observed that corpus similarity, names shared between samples, and tagger performance all decay as the time gap between the samples increases. Furthermore, we observed that the corpus similarity and names shared correlate with the tagger F-measure. These results show that named entity recognition systems may become obsolete in a short period of time.</abstract>
<identifier type="citekey">mota-grishman-2008-ne</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/303_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Is this NE tagger getting old?
%A Mota, Cristina
%A Grishman, Ralph
%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 mota-grishman-2008-ne
%X This paper focuses on the influence of changing the text time frame on the performance of a named entity tagger. We followed a twofold approach to investigate this subject: on the one hand, we analyzed a corpus that spans 8 years, and, on the other hand, we assessed the performance of a name tagger trained and tested on that corpus. We created 8 samples from the corpus, each drawn from the articles for a particular year. In terms of corpus analysis, we calculated the corpus similarity and names shared between samples. To see the effect on tagger performance, we implemented a semi-supervised name tagger based on co-training; then, we trained and tested our tagger on those samples. We observed that corpus similarity, names shared between samples, and tagger performance all decay as the time gap between the samples increases. Furthermore, we observed that the corpus similarity and names shared correlate with the tagger F-measure. These results show that named entity recognition systems may become obsolete in a short period of time.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/303_paper.pdf
Markdown (Informal)
[Is this NE tagger getting old?](http://www.lrec-conf.org/proceedings/lrec2008/pdf/303_paper.pdf) (Mota & Grishman, LREC 2008)
ACL
- Cristina Mota and Ralph Grishman. 2008. Is this NE tagger getting old?. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).