@inproceedings{poelman-etal-2024-call,
title = "A Call for Consistency in Reporting Typological Diversity",
author = "Poelman, Wessel and
Ploeger, Esther and
de Lhoneux, Miryam and
Bjerva, Johannes",
editor = "Hahn, Michael and
Sorokin, Alexey and
Kumar, Ritesh and
Shcherbakov, Andreas and
Otmakhova, Yulia and
Yang, Jinrui and
Serikov, Oleg and
Rani, Priya and
Ponti, Edoardo M. and
Murado{\u{g}}lu, Saliha and
Gao, Rena and
Cotterell, Ryan and
Vylomova, Ekaterina",
booktitle = "Proceedings of the 6th Workshop on Research in Computational Linguistic Typology and Multilingual NLP",
month = mar,
year = "2024",
address = "St. Julian's, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.sigtyp-1.10",
pages = "75--77",
abstract = "In order to draw generalizable conclusions about the performance of multilingual models across languages, it is important to evaluate on a set of languages that captures linguistic diversity.Linguistic typology is increasingly used to justify language selection, inspired by language sampling in linguistics.However, justifications for {`}typological diversity{'} exhibit great variation, as there seems to be no set definition, methodology or consistent link to linguistic typology.In this work, we provide a systematic insight into how previous work in the ACL Anthology uses the term {`}typological diversity{'}.Our two main findings are: 1) what is meant by typologically diverse language selection is not consistent and 2) the actual typological diversity of the language sets in these papers varies greatly.We argue that, when making claims about {`}typological diversity{'}, an operationalization of this should be included.A systematic approach that quantifies this claim, also with respect to the number of languages used, would be even better.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="poelman-etal-2024-call">
<titleInfo>
<title>A Call for Consistency in Reporting Typological Diversity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wessel</namePart>
<namePart type="family">Poelman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Esther</namePart>
<namePart type="family">Ploeger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miryam</namePart>
<namePart type="family">de Lhoneux</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johannes</namePart>
<namePart type="family">Bjerva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 6th Workshop on Research in Computational Linguistic Typology and Multilingual NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Hahn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexey</namePart>
<namePart type="family">Sorokin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Shcherbakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulia</namePart>
<namePart type="family">Otmakhova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinrui</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oleg</namePart>
<namePart type="family">Serikov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Priya</namePart>
<namePart type="family">Rani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Edoardo</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Ponti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saliha</namePart>
<namePart type="family">Muradoğlu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rena</namePart>
<namePart type="family">Gao</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>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Vylomova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In order to draw generalizable conclusions about the performance of multilingual models across languages, it is important to evaluate on a set of languages that captures linguistic diversity.Linguistic typology is increasingly used to justify language selection, inspired by language sampling in linguistics.However, justifications for ‘typological diversity’ exhibit great variation, as there seems to be no set definition, methodology or consistent link to linguistic typology.In this work, we provide a systematic insight into how previous work in the ACL Anthology uses the term ‘typological diversity’.Our two main findings are: 1) what is meant by typologically diverse language selection is not consistent and 2) the actual typological diversity of the language sets in these papers varies greatly.We argue that, when making claims about ‘typological diversity’, an operationalization of this should be included.A systematic approach that quantifies this claim, also with respect to the number of languages used, would be even better.</abstract>
<identifier type="citekey">poelman-etal-2024-call</identifier>
<location>
<url>https://aclanthology.org/2024.sigtyp-1.10</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>75</start>
<end>77</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Call for Consistency in Reporting Typological Diversity
%A Poelman, Wessel
%A Ploeger, Esther
%A de Lhoneux, Miryam
%A Bjerva, Johannes
%Y Hahn, Michael
%Y Sorokin, Alexey
%Y Kumar, Ritesh
%Y Shcherbakov, Andreas
%Y Otmakhova, Yulia
%Y Yang, Jinrui
%Y Serikov, Oleg
%Y Rani, Priya
%Y Ponti, Edoardo M.
%Y Muradoğlu, Saliha
%Y Gao, Rena
%Y Cotterell, Ryan
%Y Vylomova, Ekaterina
%S Proceedings of the 6th Workshop on Research in Computational Linguistic Typology and Multilingual NLP
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F poelman-etal-2024-call
%X In order to draw generalizable conclusions about the performance of multilingual models across languages, it is important to evaluate on a set of languages that captures linguistic diversity.Linguistic typology is increasingly used to justify language selection, inspired by language sampling in linguistics.However, justifications for ‘typological diversity’ exhibit great variation, as there seems to be no set definition, methodology or consistent link to linguistic typology.In this work, we provide a systematic insight into how previous work in the ACL Anthology uses the term ‘typological diversity’.Our two main findings are: 1) what is meant by typologically diverse language selection is not consistent and 2) the actual typological diversity of the language sets in these papers varies greatly.We argue that, when making claims about ‘typological diversity’, an operationalization of this should be included.A systematic approach that quantifies this claim, also with respect to the number of languages used, would be even better.
%U https://aclanthology.org/2024.sigtyp-1.10
%P 75-77
Markdown (Informal)
[A Call for Consistency in Reporting Typological Diversity](https://aclanthology.org/2024.sigtyp-1.10) (Poelman et al., SIGTYP-WS 2024)
ACL
- Wessel Poelman, Esther Ploeger, Miryam de Lhoneux, and Johannes Bjerva. 2024. A Call for Consistency in Reporting Typological Diversity. In Proceedings of the 6th Workshop on Research in Computational Linguistic Typology and Multilingual NLP, pages 75–77, St. Julian's, Malta. Association for Computational Linguistics.