CitiLink-Summ: Summarization of Discussion Subjects in European Portuguese Municipal Meeting Minutes
Authors: Miguel Marques, Ana Luísa Fernandes, Ana Filipa Pacheco, Rute Rebouças, Inês Cantante, José Isidro, Luís Filipe Cunha, Alípio Jorge, Nuno Guimarães, Sérgio Nunes, António Leal, Purificação Silvano, Ricardo Campos
Organizations: University of Beira Interior, Covilhã, Portugal · INESC TEC, Porto, Portugal · Universidade do Porto, Porto, Portugal · University of Macau, Macau, China
Municipal meeting minutes are formal records documenting the discussions and decisions of local government, yet their content is often lengthy, dense, and difficult for citizens to navigate. Automatic summarization can help address this challenge by producing concise summaries for each discussion subject. Despite its potential, research on summarizing discussion subjects in municipal meeting minutes remains largely unexplored, especially in low-resource languages, where the inherent complexity of these documents adds further challenges. A major bottleneck is the scarcity of datasets containing high-quality, manually crafted summaries, which limits the development and evaluation of effective summarization models for this domain. In this paper, we present CitiLink-Summ, a new corpus of European Portuguese municipal meeting minutes, comprising 100 documents and 2,322 manually hand-written summaries, each corresponding to a distinct discussion subject. Leveraging this dataset, we establish baseline results for automatic summarization in this domain, employing state-of-the-art generative models (e.g., BART, PRIMERA) as well as large language models (LLMs), evaluated with both lexical and semantic metrics such as ROUGE, BLEU, METEOR, and BERTScore. CitiLink-Summ provides the first benchmark for municipal-domain summarization in European Portuguese, offering a valuable resource for advancing NLP research on complex administrative texts.
Figures & tables
Figure 1. Dataset Statistics and JSON Schema.
Figure 2. Overall relationship between coverage and density.
Model
ROUGE
BLEU + METEOR
BERTSCORE
R-1
R-2
R-L
BLEU
METEOR
F1
PREC
RECALL
BART
63.52
49.22
58.20
36.06
55.15
83.87
84.59
83.37
BART Large
68.96
54.78
63.64
42.43
61.65
86.28
86.57
86.15
PTT5
52.36
38.21
45.26
23.65
46.44
76.90
76.12
78.15
LED
63.63
50.50
58.59
29.82
54.88
84.16
85.70
82.91
PRIMERA
66.17
54.57
61.94
29.06
57.05
85.79
87.10
84.79
Table 1. Performance of summarization models on the CitiLink-Summ dataset using lexical and semantic metrics.
Meeting documents are challenging to summarize due to their length and complex conversational structure. Existing approaches typically adopt multi-stage pipelines that extract information prior to summarization; however, these approaches often suffer from cumulative error propagation without intermediate validation, a limitation further amplified by short and low-quality reference summaries. We propose segment-level summarization via Monte Carlo Tree Search (S3), a training-free framework that constructs a final summary by composing segment-level summary candidates. S3 partitions a long document into segments and generates multiple summary candidates per segment, forming nodes of a search tree. The best-scoring combination is selected via self-reward-guided tree search and refined into the final output. Despite using a 7B model, S3 achieves performance comparable to larger 72B models while producing length-appropriate summaries.
Sangwon Ryu, Heejin Do, Jun Seo +4
GSAI, POSTECH · ETH Zurich, ETH AI Center · Agentic AI Lab, KT +2
QMSum provides no scorer, making query-focused meeting summarization results difficult to compare. We rescore or generate 15 systems under one implementation. Through a common inference port, a released 406M Fusion-in-Decoder specialist loses 6.30 ROUGE-1 when moved from capped long input to 2,000-word retrieved spans. Fine-tuning it on this span regime recovers the loss. On test it scores 36.33 ROUGE-1 versus 35.41 for our 1.2B system; the meeting-cluster 95% interval for the difference is [-0.27, +2.22], so QMSum does not statistically separate them. The smaller system uses about one-third as many total parameters and less than half the peak inference memory. Within the fixed 1.2B base, span-regime fine-tuning adds 5.29 [+4.02, +6.56], while replacing the first 4,500 transcript words with 2,000 retrieved words adds 1.55 on test and 0.29 on validation. Separately, under one concise prompt and reference-overlap scorer, a released 406M specialist exceeds five proprietary hosted models by at least 6.2 ROUGE-1, but output length and absent human or factuality evaluation limit this ordering. Conclusions are limited to QMSum and automatic metrics.
Large language models (LLMs) demonstrate strong performance in text summarization, yet their effectiveness drops significantly across languages with restricted training resources. This work addresses the challenge of query-focused summarization (QFS) in less-resourced languages, where labeled datasets and evaluation tools are limited. We present a novel QFS framework, QFS-Composer, that integrates query decomposition, question generation (QG), question answering (QA), and abstractive summarization to improve the factual alignment of a summary with user intent. We test our approach on the Slovenian language. To enable high-quality supervision and evaluation, we develop the Slovenian QA and QG models based on a Slovene LLM and adapt evaluation approaches for reference-free summary evaluation. Empirical evaluation shows that the QA-guided summarization pipeline yields improved consistency and relevance over baseline LLMs. Our work establishes an extensible methodology for advancing QFS in less-resourced languages.
Vuk Đuranović, Marko Robnik Šikonja
Faculty of Computer and Information Science, University of Ljubljana, Slovenia