| | --- |
| | language: |
| | - pt |
| | license: cc-by-nc-nd-4.0 |
| | colorTo: blue |
| | tags: |
| | - text-summarization |
| | - abstractive-summarization |
| | - portuguese |
| | - administrative-documents |
| | - municipal-meetings |
| | - bart-large-cnn |
| | library_name: transformers |
| | base_model: |
| | - facebook/bart-large-cnn |
| | --- |
| | |
| | # Bart-Large-Summarization-Council-PT: Abstractive Summarization of Portuguese Municipal Meeting Minutes Discussion Subjects |
| |
|
| | ## Model Description |
| |
|
| | **Bart-Large-Summarization-Council-PT** is an **abstractive text summarization model** based on **BART-large-cnn**, fine-tuned to produce concise and informative summaries of discussion subjects from **Portuguese municipal meeting minutes**. |
| | The model was trained on a curated and annotated corpus of official municipal meeting minutes covering a variety of administrative and political topics at the municipal level. |
| |
|
| | **Try out the model**: [Hugging Face Space Demo](https://huggingface.co/spaces/anonymous12321/Citilink-Summ-PT) |
| |
|
| | ### Key Features |
| |
|
| | - 🧾 **Abstractive Summarization** – Generates natural, human-like summaries rather than extracts. |
| | - 🇵🇹 **European Portuguese** – Optimized for official and administrative Portuguese. |
| | - 🏛️ **Domain-Specific** – Trained on municipal meeting minutes and administrative discussions. |
| | - ⚙️ **Fine-tuned BART** – Built upon `facebook/bart-base` using supervised fine-tuning. |
| | - 🧠 **Fact-Aware Generation** – Produces short summaries that preserve factual content. |
| |
|
| | --- |
| |
|
| | ## Model Details |
| |
|
| | - **Architecture:** `facebook/bart-large-cnn` |
| | - **Task:** Abstractive summarization (`text → summary`) |
| | - **Framework:** 🤗 Transformers (PyTorch) |
| | - **Tokenizer:** BART-large tokenizer (English vocabulary adapted for Portuguese text) |
| | - **Max Input Length:** 1024 tokens |
| | - **Max Summary Length:** 128 tokens |
| | - **Training Objective:** Conditional generation (cross-entropy loss) |
| | - **Dataset:** Portuguese municipal meeting minutes annotated with summaries |
| |
|
| | --- |
| |
|
| | ## How It Works |
| |
|
| | The model receives a discussion subject of a municipal meeting and outputs a short, coherent summary highlighting: |
| | - The **main subject or topic** of discussion |
| | - Any **decisions, motions, or proposals** made |
| | - The **entities or departments** involved |
| |
|
| | ### Example Usage |
| |
|
| | ```python |
| | from transformers import AutoTokenizer, AutoModelForSeq2SeqLM |
| | |
| | model_name = "anonymous12321/Bart-Large-Summarization-Council-PT" |
| | tokenizer = AutoTokenizer.from_pretrained(model_name) |
| | model = AutoModelForSeq2SeqLM.from_pretrained(model_name) |
| | |
| | text = """ |
| | 17. PROCESSO DE OBRAS N.º ***** -- EDIFIC\nPelo Senhor Presidente foi presente a esta reunião a informação n.º ****** da Secção de Urbanismo e Fiscalização -- Serviço de Obras Particulares que se anexa à presente ata. \nPonderado e analisado o assunto o Executivo Municipal deliberou por unanimidade aprovar as especialidades relativas ao processo de obras n.º ***** -- EDIFIC. |
| | """ |
| | |
| | inputs = tokenizer(text, return_tensors="pt", max_length=1024, truncation=True) |
| | summary_ids = model.generate(**inputs, max_length=128, num_beams=4, early_stopping=True) |
| | print(tokenizer.decode(summary_ids[0], skip_special_tokens=True)) |
| | |
| | ``` |
| |
|
| | # 🧾 Model Output |
| |
|
| | **Output:** |
| | > "O Executivo Municipal aprovou, por unanimidade, as especialidades relativas a um processo de obras particulares." |
| |
|
| | --- |
| |
|
| | ## 📊 Evaluation Results |
| |
|
| | ### Quantitative Metrics (on held-out test set) |
| |
|
| | | Metric | Score | Description | |
| | |:-------|:------:|:------------| |
| | | **ROUGE-1** | 0.645 | Unigram overlap between generated and reference summaries | |
| | | **ROUGE-2** | 0.521 | Bigram overlap | |
| | | **ROUGE-L** | 0.589 | Longest common subsequence overlap | |
| | | **BERTScore (F1)** | 0.849 | Semantic similarity between summary and reference | |
| |
|
| | --- |
| |
|
| | ## ⚙️ Training Details |
| |
|
| | - **Pretrained Model:** `facebook/bart-base` |
| | - **Optimizer:** AdamW (default in Hugging Face Trainer) |
| | - **Learning Rate:** 2e-5 |
| | - **Batch Size:** 4 |
| | - **Epochs:** 3 |
| | - **Scheduler:** Linear warmup |
| | - **Loss Function:** Cross-entropy |
| | - **Evaluation Metrics:** ROUGE (computed on validation set every 100 steps) |
| | - **Evaluation Strategy:** Step-based evaluation (`eval_steps=100`) |
| | - **Weight Decay:** 0.01 |
| | - **Mixed Precision (fp16):** Enabled when CUDA is available |
| |
|
| | --- |
| |
|
| | ## 📚 Dataset Description |
| |
|
| | The model was trained on a specialized dataset of **Portuguese municipal meeting minutes**, consisting of: |
| |
|
| | - Discussion Subjects from official municipal meeting minutes. |
| | - Decisions and deliberations across departments (urban planning, finance, education, etc.) |
| | - Expert-annotated summaries per discussion segment |
| |
|
| | **Dataset sources include:** |
| |
|
| | - Six Portuguese municipalities meeting minutes |
| |
|
| | --- |
| |
|
| | ## ⚠️ Limitations |
| |
|
| | - **Language Restriction:** The model is optimized for Portuguese; performance may degrade in other languages. |
| | - **Domain Dependence:** Best suited for administrative and institutional texts; less effective on informal or creative writing. |
| | - **Length Sensitivity:** Very long transcripts (>1024 tokens) are truncated; chunking may be needed for full documents. |
| | - **Generalization:** While robust within-domain, it may underperform on unseen domains or vocabulary. |
| |
|
| | --- |
| |
|
| | ## 📄 License |
| |
|
| | This model is released under the |
| | **Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (CC BY-NC-ND 4.0).** |
| |
|
| | --- |
| |
|
