@inproceedings{taslimipoor-etal-2026-mind,
title = "Mind the Phrase: Annotation and Identification of Multiword Expressions in Grammatical Error Correction",
author = "Taslimipoor, Shiva and
Bryant, Christopher and
Yuan, Zheng and
Nicholls, Diane and
Caines, Andrew and
Buttery, Paula",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.2165/",
pages = "46316--46329",
ISBN = "979-8-89176-462-0",
abstract = "Multiword Expressions (MWEs) are an important part of language competence which are both commonplace across languages and challenging for language learners to master. Since Grammatical Error Correction (GEC) systems tend to provide suggestions at the token level, they may fail to handle the semantic unity of MWEs. We present annotations of MWEs in learner English essays while identifying their intended spans. This not only allows us to analyse learner MWE errors in more detail for the first time, but also enables us to build GEC systems that provide more meaningful feedback to learners. We have annotated 1,850 essays that were previously tagged for grammatical errors with various types of MWEs. We extend an error annotation toolkit with an MWE error-type and present a method that leverages these annotations to make GEC evaluation more explainable, enabling fine-grained analysis of MWE errors. Experiments with current GEC systems show that an edit-based model fine-tuned on our dataset achieves higher F0.5 scores for the correction of common MWE error types, demonstrating its effectiveness for handling MWEs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="taslimipoor-etal-2026-mind">
<titleInfo>
<title>Mind the Phrase: Annotation and Identification of Multiword Expressions in Grammatical Error Correction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shiva</namePart>
<namePart type="family">Taslimipoor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Bryant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diane</namePart>
<namePart type="family">Nicholls</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Caines</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paula</namePart>
<namePart type="family">Buttery</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Multiword Expressions (MWEs) are an important part of language competence which are both commonplace across languages and challenging for language learners to master. Since Grammatical Error Correction (GEC) systems tend to provide suggestions at the token level, they may fail to handle the semantic unity of MWEs. We present annotations of MWEs in learner English essays while identifying their intended spans. This not only allows us to analyse learner MWE errors in more detail for the first time, but also enables us to build GEC systems that provide more meaningful feedback to learners. We have annotated 1,850 essays that were previously tagged for grammatical errors with various types of MWEs. We extend an error annotation toolkit with an MWE error-type and present a method that leverages these annotations to make GEC evaluation more explainable, enabling fine-grained analysis of MWE errors. Experiments with current GEC systems show that an edit-based model fine-tuned on our dataset achieves higher F0.5 scores for the correction of common MWE error types, demonstrating its effectiveness for handling MWEs.</abstract>
<identifier type="citekey">taslimipoor-etal-2026-mind</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.2165/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>46316</start>
<end>46329</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mind the Phrase: Annotation and Identification of Multiword Expressions in Grammatical Error Correction
%A Taslimipoor, Shiva
%A Bryant, Christopher
%A Yuan, Zheng
%A Nicholls, Diane
%A Caines, Andrew
%A Buttery, Paula
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F taslimipoor-etal-2026-mind
%X Multiword Expressions (MWEs) are an important part of language competence which are both commonplace across languages and challenging for language learners to master. Since Grammatical Error Correction (GEC) systems tend to provide suggestions at the token level, they may fail to handle the semantic unity of MWEs. We present annotations of MWEs in learner English essays while identifying their intended spans. This not only allows us to analyse learner MWE errors in more detail for the first time, but also enables us to build GEC systems that provide more meaningful feedback to learners. We have annotated 1,850 essays that were previously tagged for grammatical errors with various types of MWEs. We extend an error annotation toolkit with an MWE error-type and present a method that leverages these annotations to make GEC evaluation more explainable, enabling fine-grained analysis of MWE errors. Experiments with current GEC systems show that an edit-based model fine-tuned on our dataset achieves higher F0.5 scores for the correction of common MWE error types, demonstrating its effectiveness for handling MWEs.
%U https://aclanthology.org/2026.findings-emnlp.2165/
%P 46316-46329
Markdown (Informal)
[Mind the Phrase: Annotation and Identification of Multiword Expressions in Grammatical Error Correction](https://aclanthology.org/2026.findings-emnlp.2165/) (Taslimipoor et al., Findings 2026)
ACL