MiNER: A Two-Stage Pipeline for Metadata Extraction from Municipal Meeting Minutes

TL;DR

Municipal meeting minutes contain heterogeneous metadata that general-purpose NER struggles to extract. The authors introduce MiNER, a two-stage pipeline that first detects metadata boundaries via extractive QA and then performs domain-specific NER on the reduced text, with deslexicalization to improve cross-municipality generalization. They evaluate on the CitiLink Portuguese minutes (with English translations) against open Phi and closed Gemini LLMs, showing domain-tuned transformers outperform LLMs in accuracy, efficiency, and carbon footprint, though cross-municipality generalization remains challenging. The work also releases the CitiLink dataset and fine-tuned models, establishing a benchmark for metadata extraction in municipal minutes and enabling rapid local adaptation.

Abstract

Municipal meeting minutes are official documents of local governance, exhibiting heterogeneous formats and writing styles. Effective information retrieval (IR) requires identifying metadata such as meeting number, date, location, participants, and start/end times, elements that are rarely standardized or easy to extract automatically. Existing named entity recognition (NER) models are ill-suited to this task, as they are not adapted to such domain-specific categories. In this paper, we propose a two-stage pipeline for metadata extraction from municipal minutes. First, a question answering (QA) model identifies the opening and closing text segments containing metadata. Transformer-based models (BERTimbau and XLM-RoBERTa with and without a CRF layer) are then applied for fine-grained entity extraction and enhanced through deslexicalization. To evaluate our proposed pipeline, we benchmark both open-weight (Phi) and closed-weight (Gemini) LLMs, assessing predictive performance, inference cost, and carbon footprint. Our results demonstrate strong in-domain performance, better than larger general-purpose LLMs. However, cross-municipality evaluation reveals reduced generalization reflecting the variability and linguistic complexity of municipal records. This work establishes the first benchmark for metadata extraction from municipal meeting minutes, providing a solid foundation for future research in this domain.