Zum Inhalt springen

Nur-Lesen-Fassung: Das Forschungsinformationssystem (FIS) ist aus Sicherheitsgründen vorübergehend durch diese Nur-Lesen-Fassung ersetzt. Alle öffentlichen Inhalte und Volltexte sind weiterhin abrufbar; Anmeldung, Bearbeitung, Einreichung und Statistiken stehen nicht zur Verfügung. Bei Fragen: fis@uni-bamberg.de

Start › Publikationen › Regular-pattern-sensitive CRFs for Distant Label Interactions

Publikation

Regular-pattern-sensitive CRFs for Distant Label Interactions

Papay, Sean; Klinger, Roman; Padó, Sebastian (2025): Regular-pattern-sensitive CRFs for Distant Label Interactions, in: 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, S. 26–35, doi: 10.18653/v1/2025.xllm-1.4.

Details

Fakultät/Lehrstuhl
Autorin(nen)/Autor(en)
Padó, Sebastian
Titel des Sammelwerks
Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025)
Herausgeberin(nen)/Herausgeber des Sammelwerks
Fei, Hao; Tu, Kewei; Zhang, Yuhui; Hu, Xiang; Han, Wenjuan; Jia, Zixia; Zheng, Zilong; Cao, Yixin; Zhang, Meishan; Lu, Wei; Siddharth, N.; Øvrelid, Lilja; Xue, Nianwen; Zhang, Yue
Konferenz
1st Joint Workshop on Large Language Models and Structure Modeling
Verlagsangabe
Association for Computational Linguistics
Erscheinungsjahr
2025
ISBN
979-8-89176-286-2
Sprache(n)
Englisch
DOI
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.

Freie Schlagwort(e)
-
Peer Reviewed
ja
Internationale Verbreitung
ja
Open-Access-Zeitschrift
ja
Dokumenttyp
Konferenzveröffentlichung
URI
Datum der Freischaltung
07.08.2025
Projekt(e)

Permalink: https://fis.uni-bamberg.de/handle/uniba/109547 · Daten als JSON · Zitieren: BibTeX · RIS

Datenstand: 16.11.2026

Eingeschränkter Lesezugriff: Anmeldung, Bearbeitung und Einreichung sind vorübergehend deaktiviert.