@inproceedings{erdem-karaarslan-2026-beeparser,
title = "{B}ee{P}arser at {MWE}-2026 {PARSEME} 2.0 Subtask 1: Can Cross-Lingual Interactions Improve {MWE} Identification?",
author = "Erdem, Ahmet and
Karaarslan, Oguzhan",
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-1.18/",
pages = "144--148",
ISBN = "979-8-89176-363-0",
abstract = "This paper describes a multilingual system for automatic multiword expression identification for PARSEME 2.0 Subtask 1. We formulate MWE identification as a token-level sequence labeling problem using a BIO tagging scheme and fine-tune XLM-RoBERTa-base on PARSEME 2.0. We mainly investigate cross-lingual interactions on language pairs, and test hypotheses whether using a given language pair for training improves MWE detection performance on both or one of the languages. Then, we apply selected successful language pairs on PARSEME 2.0 MWE Identification task. Experiments are conducted independently for a subset of the languages given in PARSEME 2.0, for a total of 8 languages. Our approach achieves strong token-based and span-based F1 scores across diverse languages, and we observe that training with even distant language pairs may result in improvement on at least one of the languages. We publish our code at https://github.com/ahmeterdem1/parseme-blg505"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="erdem-karaarslan-2026-beeparser">
<titleInfo>
<title>BeeParser at MWE-2026 PARSEME 2.0 Subtask 1: Can Cross-Lingual Interactions Improve MWE Identification?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ahmet</namePart>
<namePart type="family">Erdem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oguzhan</namePart>
<namePart type="family">Karaarslan</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>This paper describes a multilingual system for automatic multiword expression identification for PARSEME 2.0 Subtask 1. We formulate MWE identification as a token-level sequence labeling problem using a BIO tagging scheme and fine-tune XLM-RoBERTa-base on PARSEME 2.0. We mainly investigate cross-lingual interactions on language pairs, and test hypotheses whether using a given language pair for training improves MWE detection performance on both or one of the languages. Then, we apply selected successful language pairs on PARSEME 2.0 MWE Identification task. Experiments are conducted independently for a subset of the languages given in PARSEME 2.0, for a total of 8 languages. Our approach achieves strong token-based and span-based F1 scores across diverse languages, and we observe that training with even distant language pairs may result in improvement on at least one of the languages. We publish our code at https://github.com/ahmeterdem1/parseme-blg505</abstract>
<identifier type="citekey">erdem-karaarslan-2026-beeparser</identifier>
<location>
<url>https://aclanthology.org/2026.mwe-1.18/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>144</start>
<end>148</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BeeParser at MWE-2026 PARSEME 2.0 Subtask 1: Can Cross-Lingual Interactions Improve MWE Identification?
%A Erdem, Ahmet
%A Karaarslan, Oguzhan
%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 erdem-karaarslan-2026-beeparser
%X This paper describes a multilingual system for automatic multiword expression identification for PARSEME 2.0 Subtask 1. We formulate MWE identification as a token-level sequence labeling problem using a BIO tagging scheme and fine-tune XLM-RoBERTa-base on PARSEME 2.0. We mainly investigate cross-lingual interactions on language pairs, and test hypotheses whether using a given language pair for training improves MWE detection performance on both or one of the languages. Then, we apply selected successful language pairs on PARSEME 2.0 MWE Identification task. Experiments are conducted independently for a subset of the languages given in PARSEME 2.0, for a total of 8 languages. Our approach achieves strong token-based and span-based F1 scores across diverse languages, and we observe that training with even distant language pairs may result in improvement on at least one of the languages. We publish our code at https://github.com/ahmeterdem1/parseme-blg505
%U https://aclanthology.org/2026.mwe-1.18/
%P 144-148
Markdown (Informal)
[BeeParser at MWE-2026 PARSEME 2.0 Subtask 1: Can Cross-Lingual Interactions Improve MWE Identification?](https://aclanthology.org/2026.mwe-1.18/) (Erdem & Karaarslan, MWE 2026)
ACL