@inproceedings{EzqGomVilEMNLP2026,
    title = "Bringing Emerging Architectures to Sequence Labeling in {NLP}",
    author = "Ezquerro, Ana  and
      G{\'o}mez-Rodr{\'i}guez, Carlos  and
      Vilares, David",
    editor = "Demberg, Vera  and
      Inui, Kentaro  and
      Marquez, Llu{\'i}s",
    booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.eacl-long.227/",
    doi = "10.18653/v1/2026.eacl-long.227",
    pages = "4886--4909",
    ISBN = "979-8-89176-380-7",
    abstract = "Pretrained Transformer encoders are the dominant approach to sequence labeling. While some alternative architectures-such as xLSTMs, structured state-space models, diffusion models, and adversarial learning-have shown promise in language modeling, few have been applied to sequence labeling, and mostly on flat or simplified tasks. We study how these architectures adapt across tagging tasks that vary in structural complexity, label space, and token dependencies, with evaluation spanning multiple languages. We find that the strong performance previously observed in simpler settings does not always generalize well across languages or datasets, nor does it extend to more complex structured tasks."
}