@inproceedings{gerlach-etal-2021-paradigm,
title = "Paradigm Clustering with Weighted Edit Distance",
author = "Gerlach, Andrew and
Wiemerslage, Adam and
Kann, Katharina",
editor = "Nicolai, Garrett and
Gorman, Kyle and
Cotterell, Ryan",
booktitle = "Proceedings of the 18th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.sigmorphon-1.12",
doi = "10.18653/v1/2021.sigmorphon-1.12",
pages = "107--114",
abstract = "This paper describes our system for the SIGMORPHON 2021 Shared Task on Unsupervised Morphological Paradigm Clustering, which asks participants to group inflected forms together according their underlying lemma without the aid of annotated training data. We employ agglomerative clustering to group word forms together using a metric that combines an orthographic distance and a semantic distance from word embeddings. We experiment with two variations of an edit distance-based model for quantifying orthographic distance, but, due to time constraints, our system does not improve over the shared task{'}s baseline system.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gerlach-etal-2021-paradigm">
<titleInfo>
<title>Paradigm Clustering with Weighted Edit Distance</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Gerlach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Wiemerslage</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katharina</namePart>
<namePart type="family">Kann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology</title>
</titleInfo>
<name type="personal">
<namePart type="given">Garrett</namePart>
<namePart type="family">Nicolai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyle</namePart>
<namePart type="family">Gorman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes our system for the SIGMORPHON 2021 Shared Task on Unsupervised Morphological Paradigm Clustering, which asks participants to group inflected forms together according their underlying lemma without the aid of annotated training data. We employ agglomerative clustering to group word forms together using a metric that combines an orthographic distance and a semantic distance from word embeddings. We experiment with two variations of an edit distance-based model for quantifying orthographic distance, but, due to time constraints, our system does not improve over the shared task’s baseline system.</abstract>
<identifier type="citekey">gerlach-etal-2021-paradigm</identifier>
<identifier type="doi">10.18653/v1/2021.sigmorphon-1.12</identifier>
<location>
<url>https://aclanthology.org/2021.sigmorphon-1.12</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>107</start>
<end>114</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Paradigm Clustering with Weighted Edit Distance
%A Gerlach, Andrew
%A Wiemerslage, Adam
%A Kann, Katharina
%Y Nicolai, Garrett
%Y Gorman, Kyle
%Y Cotterell, Ryan
%S Proceedings of the 18th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F gerlach-etal-2021-paradigm
%X This paper describes our system for the SIGMORPHON 2021 Shared Task on Unsupervised Morphological Paradigm Clustering, which asks participants to group inflected forms together according their underlying lemma without the aid of annotated training data. We employ agglomerative clustering to group word forms together using a metric that combines an orthographic distance and a semantic distance from word embeddings. We experiment with two variations of an edit distance-based model for quantifying orthographic distance, but, due to time constraints, our system does not improve over the shared task’s baseline system.
%R 10.18653/v1/2021.sigmorphon-1.12
%U https://aclanthology.org/2021.sigmorphon-1.12
%U https://doi.org/10.18653/v1/2021.sigmorphon-1.12
%P 107-114
Markdown (Informal)
[Paradigm Clustering with Weighted Edit Distance](https://aclanthology.org/2021.sigmorphon-1.12) (Gerlach et al., SIGMORPHON 2021)
ACL
- Andrew Gerlach, Adam Wiemerslage, and Katharina Kann. 2021. Paradigm Clustering with Weighted Edit Distance. In Proceedings of the 18th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 107–114, Online. Association for Computational Linguistics.