@inproceedings{papay-etal-2025-regular,
    title = "Regular-pattern-sensitive {CRF}s for Distant Label Interactions",
    author = "Papay, Sean  and
      Klinger, Roman  and
      Pad{\'o}, Sebastian",
    editor = "Fei, Hao  and
      Tu, Kewei  and
      Zhang, Yuhui  and
      Hu, Xiang  and
      Han, Wenjuan  and
      Jia, Zixia  and
      Zheng, Zilong  and
      Cao, Yixin  and
      Zhang, Meishan  and
      Lu, Wei  and
      Siddharth, N.  and
      {\O}vrelid, Lilja  and
      Xue, Nianwen  and
      Zhang, Yue",
    booktitle = "Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025)",
    month = aug,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/acl25-workshop-ingestion/2025.xllm-1.4/",
    pages = "26--35",
    ISBN = "979-8-89176-286-2",
    abstract = "While LLMs have grown popular in sequence labeling, linear-chain conditionalrandom fields (CRFs) remain a popular alternativewith the ability to directly model interactions between labels.However, the Markov assumption limits them to interactions between adjacent labels.Weighted finite-state transducers (FSTs), in contrast, can modeldistant label{--}label interactions, but exact label inference is intractable in general.In this work, we present regular-pattern-sensitiveCRFs (RPCRFs), a method of enriching standardlinear-chain CRFs with the ability to learnlong-distance label interactions through user-specified patterns.This approach allows users to write regular-expressionlabel patterns concisely specifying which types of interactionsthe model should take into account, allowingthe model to learn from data whether and inwhich contexts these patterns occur. The resultcan be interpreted alternatively as a CRF augmented with additional,non-local potentials,or as a finite-state transducer whose structureis defined by a set of easily-interpretable patterns.Critically, exact training and inferenceare tractable for many pattern sets. We detailhow an RPCRF can be automatically constructed from a set of user-specified patterns,and demonstrate the model{'}s effectiveness ona sequence of three synthetic sequence modeling datasets."
}