@inproceedings{moritz-etal-2018-method,
title = "A Method for Human-Interpretable Paraphrasticality Prediction",
author = {Moritz, Maria and
Hellrich, Johannes and
B{\"u}chel, Sven},
editor = "Alex, Beatrice and
Degaetano-Ortlieb, Stefania and
Feldman, Anna and
Kazantseva, Anna and
Reiter, Nils and
Szpakowicz, Stan",
booktitle = "Proceedings of the Second Joint {SIGHUM} Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature",
month = aug,
year = "2018",
address = "Santa Fe, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-4513",
pages = "113--118",
abstract = "The detection of reused text is important in a wide range of disciplines. However, even as research in the field of plagiarism detection is constantly improving, heavily modified or paraphrased text is still challenging for current methodologies. For historical texts, these problems are even more severe, since text sources were often subject to stronger and more frequent modifications. Despite the need for tools to automate text criticism, e.g., tracing modifications in historical text, algorithmic support is still limited. While current techniques can tell if and how frequently a text has been modified, very little work has been done on determining the degree and kind of paraphrastic modification{---}despite such information being of substantial interest to scholars. We present a human-interpretable, feature-based method to measure paraphrastic modification. Evaluating our technique on three data sets, we find that our approach performs competitive to text similarity scores borrowed from machine translation evaluation, being much harder to interpret.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="moritz-etal-2018-method">
<titleInfo>
<title>A Method for Human-Interpretable Paraphrasticality Prediction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Moritz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johannes</namePart>
<namePart type="family">Hellrich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sven</namePart>
<namePart type="family">Büchel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature</title>
</titleInfo>
<name type="personal">
<namePart type="given">Beatrice</namePart>
<namePart type="family">Alex</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefania</namePart>
<namePart type="family">Degaetano-Ortlieb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Feldman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Kazantseva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nils</namePart>
<namePart type="family">Reiter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stan</namePart>
<namePart type="family">Szpakowicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Santa Fe, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The detection of reused text is important in a wide range of disciplines. However, even as research in the field of plagiarism detection is constantly improving, heavily modified or paraphrased text is still challenging for current methodologies. For historical texts, these problems are even more severe, since text sources were often subject to stronger and more frequent modifications. Despite the need for tools to automate text criticism, e.g., tracing modifications in historical text, algorithmic support is still limited. While current techniques can tell if and how frequently a text has been modified, very little work has been done on determining the degree and kind of paraphrastic modification—despite such information being of substantial interest to scholars. We present a human-interpretable, feature-based method to measure paraphrastic modification. Evaluating our technique on three data sets, we find that our approach performs competitive to text similarity scores borrowed from machine translation evaluation, being much harder to interpret.</abstract>
<identifier type="citekey">moritz-etal-2018-method</identifier>
<location>
<url>https://aclanthology.org/W18-4513</url>
</location>
<part>
<date>2018-08</date>
<extent unit="page">
<start>113</start>
<end>118</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Method for Human-Interpretable Paraphrasticality Prediction
%A Moritz, Maria
%A Hellrich, Johannes
%A Büchel, Sven
%Y Alex, Beatrice
%Y Degaetano-Ortlieb, Stefania
%Y Feldman, Anna
%Y Kazantseva, Anna
%Y Reiter, Nils
%Y Szpakowicz, Stan
%S Proceedings of the Second Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature
%D 2018
%8 August
%I Association for Computational Linguistics
%C Santa Fe, New Mexico
%F moritz-etal-2018-method
%X The detection of reused text is important in a wide range of disciplines. However, even as research in the field of plagiarism detection is constantly improving, heavily modified or paraphrased text is still challenging for current methodologies. For historical texts, these problems are even more severe, since text sources were often subject to stronger and more frequent modifications. Despite the need for tools to automate text criticism, e.g., tracing modifications in historical text, algorithmic support is still limited. While current techniques can tell if and how frequently a text has been modified, very little work has been done on determining the degree and kind of paraphrastic modification—despite such information being of substantial interest to scholars. We present a human-interpretable, feature-based method to measure paraphrastic modification. Evaluating our technique on three data sets, we find that our approach performs competitive to text similarity scores borrowed from machine translation evaluation, being much harder to interpret.
%U https://aclanthology.org/W18-4513
%P 113-118
Markdown (Informal)
[A Method for Human-Interpretable Paraphrasticality Prediction](https://aclanthology.org/W18-4513) (Moritz et al., LaTeCH 2018)
ACL
- Maria Moritz, Johannes Hellrich, and Sven Büchel. 2018. A Method for Human-Interpretable Paraphrasticality Prediction. In Proceedings of the Second Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature, pages 113–118, Santa Fe, New Mexico. Association for Computational Linguistics.