BibNER-Werk: Bibliographic NER for Historical German Catalogs
Open Access
- 13 October 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Abstract
General-purpose named entity recognition does not identify the title and responsible person needed to link historical German bibliographic catalog strings in the Deutsche Digitale Bibliothek (DDB) to GND1 Work authorities, since the task’s label set and centuries-spanning historical register have no counterpart in standard training corpora. This paper uses ISBD punctuation as a tiered silver labeling signal and evaluates a deterministic rule-based baseline alongside zero-shot, few-shot, and fine-tuned GLiNER-multi and fine-tuned XLM-R-large on a stratified, human-annotated gold set. The rule-based baseline beats both fine-tuned systems on untrained data; on trained data, only GLiNER-multi’s fine-tuning gains a real, confirmed precision advantage, and XLM-R-large’s never surpasses the rule.Keywords
This publication has 14 references indexed in Scilit:
- MiNER: A Two-Stage Pipeline for Metadata Extraction from Municipal Meeting Minutes2026
- Weakly Supervised Named Entity Recognition for Historical Texts2026
- BookReconciler: An Open-Source Tool for Metadata Enrichment and Work-Level Clustering2025
- GLiNER: Generalist Model for Named Entity Recognition using Bidirectional Transformer2024
- Named Entity Recognition and Classification in Historical Documents: A SurveyACM Computing Surveys, 2023
- Unsupervised Cross-lingual Representation Learning at Scale2020
- FRBRization of MARC records in multiple catalogs2010
- Inter-Coder Agreement for Computational LinguisticsComputational Linguistics, 2008
- Interval Estimation for a Binomial ProportionStatistical Science, 2001
- An Introduction to the Bootstrap1994