@inproceedings{mott-etal-2020-morphological,
title = "Morphological Segmentation for Low Resource Languages",
author = "Mott, Justin and
Bies, Ann and
Strassel, Stephanie and
Kodner, Jordan and
Richter, Caitlin and
Xu, Hongzhi and
Marcus, Mitchell",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.493",
pages = "3996--4002",
abstract = "This paper describes a new morphology resource created by Linguistic Data Consortium and the University of Pennsylvania for the DARPA LORELEI Program. The data consists of approximately 2000 tokens annotated for morphological segmentation in each of 9 low resource languages, along with root information for 7 of the languages. The languages annotated show a broad diversity of typological features. A minimal annotation scheme for segmentation was developed such that it could capture the patterns of a wide range of languages and also be performed reliably by non-linguist annotators. The basic annotation guidelines were designed to be language-independent, but included language-specific morphological paradigms and other specifications. The resulting annotated corpus is designed to support and stimulate the development of unsupervised morphological segmenters and analyzers by providing a gold standard for their evaluation on a more typologically diverse set of languages than has previously been available. By providing root annotation, this corpus is also a step toward supporting research in identifying richer morphological structures than simple morpheme boundaries.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mott-etal-2020-morphological">
<titleInfo>
<title>Morphological Segmentation for Low Resource Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Justin</namePart>
<namePart type="family">Mott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ann</namePart>
<namePart type="family">Bies</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephanie</namePart>
<namePart type="family">Strassel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Kodner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Caitlin</namePart>
<namePart type="family">Richter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongzhi</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mitchell</namePart>
<namePart type="family">Marcus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</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>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>This paper describes a new morphology resource created by Linguistic Data Consortium and the University of Pennsylvania for the DARPA LORELEI Program. The data consists of approximately 2000 tokens annotated for morphological segmentation in each of 9 low resource languages, along with root information for 7 of the languages. The languages annotated show a broad diversity of typological features. A minimal annotation scheme for segmentation was developed such that it could capture the patterns of a wide range of languages and also be performed reliably by non-linguist annotators. The basic annotation guidelines were designed to be language-independent, but included language-specific morphological paradigms and other specifications. The resulting annotated corpus is designed to support and stimulate the development of unsupervised morphological segmenters and analyzers by providing a gold standard for their evaluation on a more typologically diverse set of languages than has previously been available. By providing root annotation, this corpus is also a step toward supporting research in identifying richer morphological structures than simple morpheme boundaries.</abstract>
<identifier type="citekey">mott-etal-2020-morphological</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.493</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>3996</start>
<end>4002</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Morphological Segmentation for Low Resource Languages
%A Mott, Justin
%A Bies, Ann
%A Strassel, Stephanie
%A Kodner, Jordan
%A Richter, Caitlin
%A Xu, Hongzhi
%A Marcus, Mitchell
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F mott-etal-2020-morphological
%X This paper describes a new morphology resource created by Linguistic Data Consortium and the University of Pennsylvania for the DARPA LORELEI Program. The data consists of approximately 2000 tokens annotated for morphological segmentation in each of 9 low resource languages, along with root information for 7 of the languages. The languages annotated show a broad diversity of typological features. A minimal annotation scheme for segmentation was developed such that it could capture the patterns of a wide range of languages and also be performed reliably by non-linguist annotators. The basic annotation guidelines were designed to be language-independent, but included language-specific morphological paradigms and other specifications. The resulting annotated corpus is designed to support and stimulate the development of unsupervised morphological segmenters and analyzers by providing a gold standard for their evaluation on a more typologically diverse set of languages than has previously been available. By providing root annotation, this corpus is also a step toward supporting research in identifying richer morphological structures than simple morpheme boundaries.
%U https://aclanthology.org/2020.lrec-1.493
%P 3996-4002
Markdown (Informal)
[Morphological Segmentation for Low Resource Languages](https://aclanthology.org/2020.lrec-1.493) (Mott et al., LREC 2020)
ACL
- Justin Mott, Ann Bies, Stephanie Strassel, Jordan Kodner, Caitlin Richter, Hongzhi Xu, and Mitchell Marcus. 2020. Morphological Segmentation for Low Resource Languages. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 3996–4002, Marseille, France. European Language Resources Association.