@inproceedings{hulsing-etal-2026-ipn,
title = "{IPN} at {MWE}-2026 {PARSEME} 2.0 Subtask 1: {MWE} Identification via Related Languages and Harnessing Thinking Mode",
author = {H{\"u}lsing, Anna and
Michael, Noah-Manuel and
Melanchthon, Daniel Mora and
Horbach, Andrea},
editor = {Ojha, Atul Kr. and
Mititelu, Verginica Barbu and
Constant, Mathieu and
Stoyanova, Ivelina and
Do{\u{g}}ru{\"o}z, A. Seza and
Rademaker, Alexandre},
booktitle = "Proceedings of the 22nd Workshop on Multiword Expressions ({MWE} 2026)",
month = mar,
year = "2026",
address = "Rabat, Marocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.mwe-1.24/",
pages = "177--186",
ISBN = "979-8-89176-363-0",
abstract = "We present IPN, our system for Subtask 1 of the PARSEME 2.0 Shared Task, which targets the identification of MWEs in 17 languages. Overall, IPN outperformed a much larger-parameter baseline model, yet a performance gap to the top-performing systems remains. To better understand these results, we investigate Qwen3-32B{'}s suitability for mono-, cross- and multilingual MWE identification. We also explore whether this model benefits from prepending automatically generated thinking data to the gold label during instruction-tuning. We find that target language data is vital for instruction-tuning. Prepending generated thinking data to a subset of the training data slightly improves performance for two out of three languages, but more detailed evaluation is required."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hulsing-etal-2026-ipn">
<titleInfo>
<title>IPN at MWE-2026 PARSEME 2.0 Subtask 1: MWE Identification via Related Languages and Harnessing Thinking Mode</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Hülsing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Noah-Manuel</namePart>
<namePart type="family">Michael</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="given">Mora</namePart>
<namePart type="family">Melanchthon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Horbach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 22nd Workshop on Multiword Expressions (MWE 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Verginica</namePart>
<namePart type="given">Barbu</namePart>
<namePart type="family">Mititelu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mathieu</namePart>
<namePart type="family">Constant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivelina</namePart>
<namePart type="family">Stoyanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">Seza</namePart>
<namePart type="family">Doğruöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandre</namePart>
<namePart type="family">Rademaker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Marocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-363-0</identifier>
</relatedItem>
<abstract>We present IPN, our system for Subtask 1 of the PARSEME 2.0 Shared Task, which targets the identification of MWEs in 17 languages. Overall, IPN outperformed a much larger-parameter baseline model, yet a performance gap to the top-performing systems remains. To better understand these results, we investigate Qwen3-32B’s suitability for mono-, cross- and multilingual MWE identification. We also explore whether this model benefits from prepending automatically generated thinking data to the gold label during instruction-tuning. We find that target language data is vital for instruction-tuning. Prepending generated thinking data to a subset of the training data slightly improves performance for two out of three languages, but more detailed evaluation is required.</abstract>
<identifier type="citekey">hulsing-etal-2026-ipn</identifier>
<location>
<url>https://aclanthology.org/2026.mwe-1.24/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>177</start>
<end>186</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T IPN at MWE-2026 PARSEME 2.0 Subtask 1: MWE Identification via Related Languages and Harnessing Thinking Mode
%A Hülsing, Anna
%A Michael, Noah-Manuel
%A Melanchthon, Daniel Mora
%A Horbach, Andrea
%Y Ojha, Atul Kr.
%Y Mititelu, Verginica Barbu
%Y Constant, Mathieu
%Y Stoyanova, Ivelina
%Y Doğruöz, A. Seza
%Y Rademaker, Alexandre
%S Proceedings of the 22nd Workshop on Multiword Expressions (MWE 2026)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Marocco
%@ 979-8-89176-363-0
%F hulsing-etal-2026-ipn
%X We present IPN, our system for Subtask 1 of the PARSEME 2.0 Shared Task, which targets the identification of MWEs in 17 languages. Overall, IPN outperformed a much larger-parameter baseline model, yet a performance gap to the top-performing systems remains. To better understand these results, we investigate Qwen3-32B’s suitability for mono-, cross- and multilingual MWE identification. We also explore whether this model benefits from prepending automatically generated thinking data to the gold label during instruction-tuning. We find that target language data is vital for instruction-tuning. Prepending generated thinking data to a subset of the training data slightly improves performance for two out of three languages, but more detailed evaluation is required.
%U https://aclanthology.org/2026.mwe-1.24/
%P 177-186
Markdown (Informal)
[IPN at MWE-2026 PARSEME 2.0 Subtask 1: MWE Identification via Related Languages and Harnessing Thinking Mode](https://aclanthology.org/2026.mwe-1.24/) (Hülsing et al., MWE 2026)
ACL