@inproceedings{ide-etal-2025-coam,
title = "{C}o{AM}: Corpus of All-Type Multiword Expressions",
author = "Ide, Yusuke and
Tanner, Joshua and
Nohejl, Adam and
Hoffman, Jacob and
Vasselli, Justin and
Kamigaito, Hidetaka and
Watanabe, Taro",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.1311/",
doi = "10.18653/v1/2025.acl-long.1311",
pages = "27004--27021",
ISBN = "979-8-89176-251-0",
abstract = "Multiword expressions (MWEs) refer to idiomatic sequences of multiple words.MWE identification, i.e., detecting MWEs in text, can play a key role in downstream tasks such as machine translation, but existing datasets for the task are inconsistently annotated, limited to a single type of MWE, or limited in size.To enable reliable and comprehensive evaluation, we created CoAM: Corpus of All-Type Multiword Expressions, a dataset of 1.3K sentences constructed through a multi-step process to enhance data quality consisting of human annotation, human review, and automated consistency checking.Additionally, for the first time in a dataset of MWE identification, CoAM{'}s MWEs are tagged with MWE types, such as Noun and Verb, enabling fine-grained error analysis.Annotations for CoAM were collected using a new interface created with our interface generator, which allows easy and flexible annotation of MWEs in any form.Through experiments using CoAM, we find that a fine-tuned large language model outperforms MWEasWSD, which achieved the state-of-the-art performance on the DiMSUM dataset.Furthermore, analysis using our MWE type tagged data reveals that Verb MWEs are easier than Noun MWEs to identify across approaches."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ide-etal-2025-coam">
<titleInfo>
<title>CoAM: Corpus of All-Type Multiword Expressions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yusuke</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joshua</namePart>
<namePart type="family">Tanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Nohejl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jacob</namePart>
<namePart type="family">Hoffman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Justin</namePart>
<namePart type="family">Vasselli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hidetaka</namePart>
<namePart type="family">Kamigaito</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taro</namePart>
<namePart type="family">Watanabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>Multiword expressions (MWEs) refer to idiomatic sequences of multiple words.MWE identification, i.e., detecting MWEs in text, can play a key role in downstream tasks such as machine translation, but existing datasets for the task are inconsistently annotated, limited to a single type of MWE, or limited in size.To enable reliable and comprehensive evaluation, we created CoAM: Corpus of All-Type Multiword Expressions, a dataset of 1.3K sentences constructed through a multi-step process to enhance data quality consisting of human annotation, human review, and automated consistency checking.Additionally, for the first time in a dataset of MWE identification, CoAM’s MWEs are tagged with MWE types, such as Noun and Verb, enabling fine-grained error analysis.Annotations for CoAM were collected using a new interface created with our interface generator, which allows easy and flexible annotation of MWEs in any form.Through experiments using CoAM, we find that a fine-tuned large language model outperforms MWEasWSD, which achieved the state-of-the-art performance on the DiMSUM dataset.Furthermore, analysis using our MWE type tagged data reveals that Verb MWEs are easier than Noun MWEs to identify across approaches.</abstract>
<identifier type="citekey">ide-etal-2025-coam</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.1311</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.1311/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>27004</start>
<end>27021</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CoAM: Corpus of All-Type Multiword Expressions
%A Ide, Yusuke
%A Tanner, Joshua
%A Nohejl, Adam
%A Hoffman, Jacob
%A Vasselli, Justin
%A Kamigaito, Hidetaka
%A Watanabe, Taro
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F ide-etal-2025-coam
%X Multiword expressions (MWEs) refer to idiomatic sequences of multiple words.MWE identification, i.e., detecting MWEs in text, can play a key role in downstream tasks such as machine translation, but existing datasets for the task are inconsistently annotated, limited to a single type of MWE, or limited in size.To enable reliable and comprehensive evaluation, we created CoAM: Corpus of All-Type Multiword Expressions, a dataset of 1.3K sentences constructed through a multi-step process to enhance data quality consisting of human annotation, human review, and automated consistency checking.Additionally, for the first time in a dataset of MWE identification, CoAM’s MWEs are tagged with MWE types, such as Noun and Verb, enabling fine-grained error analysis.Annotations for CoAM were collected using a new interface created with our interface generator, which allows easy and flexible annotation of MWEs in any form.Through experiments using CoAM, we find that a fine-tuned large language model outperforms MWEasWSD, which achieved the state-of-the-art performance on the DiMSUM dataset.Furthermore, analysis using our MWE type tagged data reveals that Verb MWEs are easier than Noun MWEs to identify across approaches.
%R 10.18653/v1/2025.acl-long.1311
%U https://aclanthology.org/2025.acl-long.1311/
%U https://doi.org/10.18653/v1/2025.acl-long.1311
%P 27004-27021
Markdown (Informal)
[CoAM: Corpus of All-Type Multiword Expressions](https://aclanthology.org/2025.acl-long.1311/) (Ide et al., ACL 2025)
ACL
- Yusuke Ide, Joshua Tanner, Adam Nohejl, Jacob Hoffman, Justin Vasselli, Hidetaka Kamigaito, and Taro Watanabe. 2025. CoAM: Corpus of All-Type Multiword Expressions. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 27004–27021, Vienna, Austria. Association for Computational Linguistics.