Skip to content

Read-only version: For security reasons, the Research Information System (FIS) has been temporarily replaced by this read-only version. All public content and full texts remain available; login, editing, submission and statistics are not available. Questions: fis@uni-bamberg.de

Home › Publications › Regular-pattern-sensitive CRFs for Distant Label Interactions

Publication

Regular-pattern-sensitive CRFs for Distant Label Interactions

Papay, Sean; Klinger, Roman; Padó, Sebastian (2026): Regular-pattern-sensitive CRFs for Distant Label Interactions, in: Bamberg: Otto-Friedrich-Universität, S. 26–35.

Details

Faculty/Chair
Faculty/Professorship
Author
Padó, Sebastian
Publisher Information
Otto-Friedrich-Universität : Bamberg
Year of publication
2026
Source/Other editions
Hao Fei, Kewei Tu, Yuhui Zhang, u. a. (Hrsg.), Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025), Association for Computational Linguistics, 2025, S. 26–35, ISBN: 979-8-89176-286-2
Year of first publication
2025
Language
English
Licence
URN
Abstract

While LLMs have grown popular in sequence labeling, linear-chain conditional random fields (CRFs) remain a popular alternative with 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 model distant label–label interactions, but exact label inference is intractable in general. In this work, we present regular-pattern-sensitive CRFs (RPCRFs), a method of enriching standard linear-chain CRFs with the ability to learn long-distance label interactions through userspecified patterns. This approach allows users to write regular-expression label patterns concisely specifying which types of interactions the model should take into account, allowing the model to learn from data whether and in which contexts these patterns occur. The result can be interpreted alternatively as a CRF augmented with additional, non-local potentials, or as a finite-state transducer whose structure is defined by a set of easily-interpretable patterns. Critically, exact training and inference are tractable for many pattern sets. We detail how an RPCRF can be automatically constructed from a set of user-specified patterns, and demonstrate the model’s effectiveness on a sequence of three synthetic sequence modeling datasets.

Keywords
-
Peer Reviewed
yes
International Distribution
yes
Open Access Journal
yes
Type
Conferenceobject
URI
Activation date
2026-03-24
Project(s)

Permalink: https://fis.uni-bamberg.de/handle/uniba/114408 · Data as JSON · Cite: BibTeX · RIS

Data as of: 2026-11-16

Restricted read-only access: login, editing and submission are temporarily disabled.