@inproceedings{otterbacher-radev-2008-modeling,
title = "Modeling Document Dynamics: an Evolutionary Approach",
author = "Otterbacher, Jahna and
Radev, Dragomir",
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/115_paper.pdf",
abstract = "News articles about the same event published over time have properties that challenge NLP and IR applications. A cluster of such texts typically exhibits instances of paraphrase and contradiction, as sources update the facts surrounding the story, often due to an ongoing investigation. The current hypothesis is that the stories evolve over time, beginning with the first text published on a given topic. This is tested using a phylogenetic approach as well as one based on language modeling. The fit of the evolutionary models is evaluated with respect to how well they facilitate the recovery of chronological relationships between the documents. Over all data clusters, the language modeling approach consistently outperforms the phylogenetics model. However, on manually collected clusters in which the documents are published within short time spans of one another, both have a similar performance, and produce statistically significant results on the document chronology recovery evaluation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="otterbacher-radev-2008-modeling">
<titleInfo>
<title>Modeling Document Dynamics: an Evolutionary Approach</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jahna</namePart>
<namePart type="family">Otterbacher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dragomir</namePart>
<namePart type="family">Radev</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>News articles about the same event published over time have properties that challenge NLP and IR applications. A cluster of such texts typically exhibits instances of paraphrase and contradiction, as sources update the facts surrounding the story, often due to an ongoing investigation. The current hypothesis is that the stories evolve over time, beginning with the first text published on a given topic. This is tested using a phylogenetic approach as well as one based on language modeling. The fit of the evolutionary models is evaluated with respect to how well they facilitate the recovery of chronological relationships between the documents. Over all data clusters, the language modeling approach consistently outperforms the phylogenetics model. However, on manually collected clusters in which the documents are published within short time spans of one another, both have a similar performance, and produce statistically significant results on the document chronology recovery evaluation.</abstract>
<identifier type="citekey">otterbacher-radev-2008-modeling</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/115_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Modeling Document Dynamics: an Evolutionary Approach
%A Otterbacher, Jahna
%A Radev, Dragomir
%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 otterbacher-radev-2008-modeling
%X News articles about the same event published over time have properties that challenge NLP and IR applications. A cluster of such texts typically exhibits instances of paraphrase and contradiction, as sources update the facts surrounding the story, often due to an ongoing investigation. The current hypothesis is that the stories evolve over time, beginning with the first text published on a given topic. This is tested using a phylogenetic approach as well as one based on language modeling. The fit of the evolutionary models is evaluated with respect to how well they facilitate the recovery of chronological relationships between the documents. Over all data clusters, the language modeling approach consistently outperforms the phylogenetics model. However, on manually collected clusters in which the documents are published within short time spans of one another, both have a similar performance, and produce statistically significant results on the document chronology recovery evaluation.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/115_paper.pdf
Markdown (Informal)
[Modeling Document Dynamics: an Evolutionary Approach](http://www.lrec-conf.org/proceedings/lrec2008/pdf/115_paper.pdf) (Otterbacher & Radev, LREC 2008)
ACL
- Jahna Otterbacher and Dragomir Radev. 2008. Modeling Document Dynamics: an Evolutionary Approach. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).