@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://preview.aclanthology.org/ingest-eacl/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"
}