@inproceedings{volodina-etal-2021-coderoomor,
title = "{C}o{D}e{R}oo{M}or: A new dataset for non-inflectional morphology studies of {S}wedish",
author = {Volodina, Elena and
Mohammed, Yousuf Ali and
Tiedemann, Therese Lindstr{\"o}m},
editor = "Dobnik, Simon and
{\O}vrelid, Lilja",
booktitle = "Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa)",
month = may # " 31--2 " # jun,
year = "2021",
address = "Reykjavik, Iceland (Online)",
publisher = {Link{\"o}ping University Electronic Press, Sweden},
url = "https://aclanthology.org/2021.nodalida-main.18",
pages = "178--189",
abstract = "The paper introduces a new resource, CoDeRooMor, for studying the morphology of modern Swedish word formation. The approximately 16.000 lexical items in the resource have been manually segmented into word-formation morphemes, and labeled for their categories, such as prefixes, suffixes, roots, etc. Word-formation mechanisms, such as derivation and compounding have been associated with each item on the list. The article describes the selection of items for manual annotation and the principles of annotation, reports on the reliability of the manual annotation, and presents tools, resources and some first statistics. Given the{''}gold{''} nature of the resource, it is possible to use it for empirical studies as well as to develop linguistically-aware algorithms for morpheme segmentation and labeling (cf statistical subword approach). The resource will be made freely available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="volodina-etal-2021-coderoomor">
<titleInfo>
<title>CoDeRooMor: A new dataset for non-inflectional morphology studies of Swedish</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Volodina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yousuf</namePart>
<namePart type="given">Ali</namePart>
<namePart type="family">Mohammed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Therese</namePart>
<namePart type="given">Lindström</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-may 31–2 jun</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Dobnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lilja</namePart>
<namePart type="family">Øvrelid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Linköping University Electronic Press, Sweden</publisher>
<place>
<placeTerm type="text">Reykjavik, Iceland (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The paper introduces a new resource, CoDeRooMor, for studying the morphology of modern Swedish word formation. The approximately 16.000 lexical items in the resource have been manually segmented into word-formation morphemes, and labeled for their categories, such as prefixes, suffixes, roots, etc. Word-formation mechanisms, such as derivation and compounding have been associated with each item on the list. The article describes the selection of items for manual annotation and the principles of annotation, reports on the reliability of the manual annotation, and presents tools, resources and some first statistics. Given the”gold” nature of the resource, it is possible to use it for empirical studies as well as to develop linguistically-aware algorithms for morpheme segmentation and labeling (cf statistical subword approach). The resource will be made freely available.</abstract>
<identifier type="citekey">volodina-etal-2021-coderoomor</identifier>
<location>
<url>https://aclanthology.org/2021.nodalida-main.18</url>
</location>
<part>
<date>2021-may 31–2 jun</date>
<extent unit="page">
<start>178</start>
<end>189</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CoDeRooMor: A new dataset for non-inflectional morphology studies of Swedish
%A Volodina, Elena
%A Mohammed, Yousuf Ali
%A Tiedemann, Therese Lindström
%Y Dobnik, Simon
%Y Øvrelid, Lilja
%S Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa)
%D 2021
%8 may 31–2 jun
%I Linköping University Electronic Press, Sweden
%C Reykjavik, Iceland (Online)
%F volodina-etal-2021-coderoomor
%X The paper introduces a new resource, CoDeRooMor, for studying the morphology of modern Swedish word formation. The approximately 16.000 lexical items in the resource have been manually segmented into word-formation morphemes, and labeled for their categories, such as prefixes, suffixes, roots, etc. Word-formation mechanisms, such as derivation and compounding have been associated with each item on the list. The article describes the selection of items for manual annotation and the principles of annotation, reports on the reliability of the manual annotation, and presents tools, resources and some first statistics. Given the”gold” nature of the resource, it is possible to use it for empirical studies as well as to develop linguistically-aware algorithms for morpheme segmentation and labeling (cf statistical subword approach). The resource will be made freely available.
%U https://aclanthology.org/2021.nodalida-main.18
%P 178-189
Markdown (Informal)
[CoDeRooMor: A new dataset for non-inflectional morphology studies of Swedish](https://aclanthology.org/2021.nodalida-main.18) (Volodina et al., NoDaLiDa 2021)
ACL