@inproceedings{batsuren-etal-2022-sigmorphon,
title = "The {SIGMORPHON} 2022 Shared Task on Morpheme Segmentation",
author = "Batsuren, Khuyagbaatar and
Bella, G{\'a}bor and
Arora, Aryaman and
Martinovic, Viktor and
Gorman, Kyle and
{\v{Z}}abokrtsk{\'y}, Zden{\v{e}}k and
Ganbold, Amarsanaa and
Dohnalov{\'a}, {\v{S}}{\'a}rka and
{\v{S}}ev{\v{c}}{\'\i}kov{\'a}, Magda and
Pelegrinov{\'a}, Kate{\v{r}}ina and
Giunchiglia, Fausto and
Cotterell, Ryan and
Vylomova, Ekaterina",
editor = "Nicolai, Garrett and
Chodroff, Eleanor",
booktitle = "Proceedings of the 19th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology",
month = jul,
year = "2022",
address = "Seattle, Washington",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.sigmorphon-1.11",
doi = "10.18653/v1/2022.sigmorphon-1.11",
pages = "103--116",
abstract = "The SIGMORPHON 2022 shared task on morpheme segmentation challenged systems to decompose a word into a sequence of morphemes and covered most types of morphology: compounds, derivations, and inflections. Subtask 1, word-level morpheme segmentation, covered 5 million words in 9 languages (Czech, English, Spanish, Hungarian, French, Italian, Russian, Latin, Mongolian) and received 13 system submissions from 7 teams and the best system averaged 97.29{\%} F1 score across all languages, ranging English (93.84{\%}) to Latin (99.38{\%}). Subtask 2, sentence-level morpheme segmentation, covered 18,735 sentences in 3 languages (Czech, English, Mongolian), received 10 system submissions from 3 teams, and the best systems outperformed all three state-of-the-art subword tokenization methods (BPE, ULM, Morfessor2) by 30.71{\%} absolute. To facilitate error analysis and support any type of future studies, we released all system predictions, the evaluation script, and all gold standard datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="batsuren-etal-2022-sigmorphon">
<titleInfo>
<title>The SIGMORPHON 2022 Shared Task on Morpheme Segmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Khuyagbaatar</namePart>
<namePart type="family">Batsuren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gábor</namePart>
<namePart type="family">Bella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aryaman</namePart>
<namePart type="family">Arora</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viktor</namePart>
<namePart type="family">Martinovic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyle</namePart>
<namePart type="family">Gorman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zdeněk</namePart>
<namePart type="family">Žabokrtský</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amarsanaa</namePart>
<namePart type="family">Ganbold</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Šárka</namePart>
<namePart type="family">Dohnalová</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Magda</namePart>
<namePart type="family">Ševčíková</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kateřina</namePart>
<namePart type="family">Pelegrinová</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fausto</namePart>
<namePart type="family">Giunchiglia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Vylomova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th 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">Eleanor</namePart>
<namePart type="family">Chodroff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, Washington</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The SIGMORPHON 2022 shared task on morpheme segmentation challenged systems to decompose a word into a sequence of morphemes and covered most types of morphology: compounds, derivations, and inflections. Subtask 1, word-level morpheme segmentation, covered 5 million words in 9 languages (Czech, English, Spanish, Hungarian, French, Italian, Russian, Latin, Mongolian) and received 13 system submissions from 7 teams and the best system averaged 97.29% F1 score across all languages, ranging English (93.84%) to Latin (99.38%). Subtask 2, sentence-level morpheme segmentation, covered 18,735 sentences in 3 languages (Czech, English, Mongolian), received 10 system submissions from 3 teams, and the best systems outperformed all three state-of-the-art subword tokenization methods (BPE, ULM, Morfessor2) by 30.71% absolute. To facilitate error analysis and support any type of future studies, we released all system predictions, the evaluation script, and all gold standard datasets.</abstract>
<identifier type="citekey">batsuren-etal-2022-sigmorphon</identifier>
<identifier type="doi">10.18653/v1/2022.sigmorphon-1.11</identifier>
<location>
<url>https://aclanthology.org/2022.sigmorphon-1.11</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>103</start>
<end>116</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The SIGMORPHON 2022 Shared Task on Morpheme Segmentation
%A Batsuren, Khuyagbaatar
%A Bella, Gábor
%A Arora, Aryaman
%A Martinovic, Viktor
%A Gorman, Kyle
%A Žabokrtský, Zdeněk
%A Ganbold, Amarsanaa
%A Dohnalová, Šárka
%A Ševčíková, Magda
%A Pelegrinová, Kateřina
%A Giunchiglia, Fausto
%A Cotterell, Ryan
%A Vylomova, Ekaterina
%Y Nicolai, Garrett
%Y Chodroff, Eleanor
%S Proceedings of the 19th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, Washington
%F batsuren-etal-2022-sigmorphon
%X The SIGMORPHON 2022 shared task on morpheme segmentation challenged systems to decompose a word into a sequence of morphemes and covered most types of morphology: compounds, derivations, and inflections. Subtask 1, word-level morpheme segmentation, covered 5 million words in 9 languages (Czech, English, Spanish, Hungarian, French, Italian, Russian, Latin, Mongolian) and received 13 system submissions from 7 teams and the best system averaged 97.29% F1 score across all languages, ranging English (93.84%) to Latin (99.38%). Subtask 2, sentence-level morpheme segmentation, covered 18,735 sentences in 3 languages (Czech, English, Mongolian), received 10 system submissions from 3 teams, and the best systems outperformed all three state-of-the-art subword tokenization methods (BPE, ULM, Morfessor2) by 30.71% absolute. To facilitate error analysis and support any type of future studies, we released all system predictions, the evaluation script, and all gold standard datasets.
%R 10.18653/v1/2022.sigmorphon-1.11
%U https://aclanthology.org/2022.sigmorphon-1.11
%U https://doi.org/10.18653/v1/2022.sigmorphon-1.11
%P 103-116
Markdown (Informal)
[The SIGMORPHON 2022 Shared Task on Morpheme Segmentation](https://aclanthology.org/2022.sigmorphon-1.11) (Batsuren et al., SIGMORPHON 2022)
ACL
- Khuyagbaatar Batsuren, Gábor Bella, Aryaman Arora, Viktor Martinovic, Kyle Gorman, Zdeněk Žabokrtský, Amarsanaa Ganbold, Šárka Dohnalová, Magda Ševčíková, Kateřina Pelegrinová, Fausto Giunchiglia, Ryan Cotterell, and Ekaterina Vylomova. 2022. The SIGMORPHON 2022 Shared Task on Morpheme Segmentation. In Proceedings of the 19th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 103–116, Seattle, Washington. Association for Computational Linguistics.