@inproceedings{lion-bouton-etal-2022-evaluating,
title = "Evaluating Diversity of Multiword Expressions in Annotated Text",
author = "Lion-Bouton, Adam and
Ozturk, Yagmur and
Savary, Agata and
Antoine, Jean-Yves",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.290",
pages = "3285--3295",
abstract = "Diversity can be decomposed into three distinct concepts, namely: variety, balance and disparity. This paper borrows from the extensive formalization and measures of diversity developed in ecology in order to evaluate the variety and balance of multiword expression annotation produced by automatic annotation systems. The measures of richness, normalized richness, and two variations of Hill{'}s evenness are considered in this paper. We observe how these measures behave against increasingly smaller samples of gold annotations of multiword expressions and use their comportment to validate or invalidate their pertinence for multiword expressions in annotated texts. We apply the validated measures to annotations in 14 languages produced by systems during the PARSEME shared task on automatic identification of multiword expressions and on the gold versions of the corpora. We also explore the limits of such evaluation by studying the impact of lemmatization errors in the Turkish corpus used in the shared task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lion-bouton-etal-2022-evaluating">
<titleInfo>
<title>Evaluating Diversity of Multiword Expressions in Annotated Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Lion-Bouton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yagmur</namePart>
<namePart type="family">Ozturk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Agata</namePart>
<namePart type="family">Savary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jean-Yves</namePart>
<namePart type="family">Antoine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</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">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Diversity can be decomposed into three distinct concepts, namely: variety, balance and disparity. This paper borrows from the extensive formalization and measures of diversity developed in ecology in order to evaluate the variety and balance of multiword expression annotation produced by automatic annotation systems. The measures of richness, normalized richness, and two variations of Hill’s evenness are considered in this paper. We observe how these measures behave against increasingly smaller samples of gold annotations of multiword expressions and use their comportment to validate or invalidate their pertinence for multiword expressions in annotated texts. We apply the validated measures to annotations in 14 languages produced by systems during the PARSEME shared task on automatic identification of multiword expressions and on the gold versions of the corpora. We also explore the limits of such evaluation by studying the impact of lemmatization errors in the Turkish corpus used in the shared task.</abstract>
<identifier type="citekey">lion-bouton-etal-2022-evaluating</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.290</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>3285</start>
<end>3295</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Diversity of Multiword Expressions in Annotated Text
%A Lion-Bouton, Adam
%A Ozturk, Yagmur
%A Savary, Agata
%A Antoine, Jean-Yves
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F lion-bouton-etal-2022-evaluating
%X Diversity can be decomposed into three distinct concepts, namely: variety, balance and disparity. This paper borrows from the extensive formalization and measures of diversity developed in ecology in order to evaluate the variety and balance of multiword expression annotation produced by automatic annotation systems. The measures of richness, normalized richness, and two variations of Hill’s evenness are considered in this paper. We observe how these measures behave against increasingly smaller samples of gold annotations of multiword expressions and use their comportment to validate or invalidate their pertinence for multiword expressions in annotated texts. We apply the validated measures to annotations in 14 languages produced by systems during the PARSEME shared task on automatic identification of multiword expressions and on the gold versions of the corpora. We also explore the limits of such evaluation by studying the impact of lemmatization errors in the Turkish corpus used in the shared task.
%U https://aclanthology.org/2022.coling-1.290
%P 3285-3295
Markdown (Informal)
[Evaluating Diversity of Multiword Expressions in Annotated Text](https://aclanthology.org/2022.coling-1.290) (Lion-Bouton et al., COLING 2022)
ACL
- Adam Lion-Bouton, Yagmur Ozturk, Agata Savary, and Jean-Yves Antoine. 2022. Evaluating Diversity of Multiword Expressions in Annotated Text. In Proceedings of the 29th International Conference on Computational Linguistics, pages 3285–3295, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.