---
license: cc-by-nc-4.0
language:
- bn
- en
base_model: xlm-roberta-base
pipeline_tag: text-classification
library_name: onnxruntime
tags:
- bengali
- bangla
- information-extraction
- event-extraction
- onnx
- int8
- quantized
- news
---

# newsintel-event-type

Multi-label event-type router: accident / disaster / crime (a document may fire several).

Part of **NewsIntel AI** — a CPU-deployable, LLM-free pipeline that extracts structured
public-safety events (accidents, disasters, crimes) from Bangladeshi news in **Bengali and
English**. This model is stage **2 · router — accident/disaster/crime** of that chain:

```
document → relevance gate → event-type router → evidence selection
         → NER → relation extraction → knowledge graph → structured event JSON
```

## Model details

| | |
|---|---|
| Base model | `xlm-roberta-base` |
| Task | `event_type` |
| Input | `text` |
| Max length | 256 |
| Format | ONNX INT8 (dynamic quantization), ~279 MB |
| Version | `cf651b4757647` |
| Languages | Bengali (primary, ~96% of training corpus), English |

### Labels
- `accident`
- `disaster`
- `crime`

### Thresholds
- `accident`: 0.675
- `disaster`: 0.75
- `crime`: 0.55

### Decision rule
```
p = sigmoid(logits); fired[i] = p[i] >= thresholds[labels[i]]
```
These values also ship machine-readable in `model_manifest.json`, so a serving process can
consume the model without hardcoding anything.

## Evaluation

| Metric | Value |
|---|---|
| macro-F1 | 0.8841 |


## Usage

```python
from huggingface_hub import snapshot_download
import onnxruntime as ort, numpy as np
from transformers import AutoTokenizer

d = snapshot_download("saidylive/newsintel-event-type", revision="cf651b4757647",
                      allow_patterns=["model_int8.onnx", "*.json", "*.model"])
tok = AutoTokenizer.from_pretrained(d)
sess = ort.InferenceSession(f"{d}/model_int8.onnx", providers=["CPUExecutionProvider"])

enc = tok("সাভারে বাস-ট্রাকের সংঘর্ষে নিহত ২", return_tensors="np")
logits = sess.run(None, {k: v for k, v in enc.items()
                         if k in {i.name for i in sess.get_inputs()}})[0]
# decision rule (from model_manifest.json):
#   p = sigmoid(logits); fired[i] = p[i] >= thresholds[labels[i]]
```

## Training data & provenance

Trained on the **`bd_eng_news_daily`** Kaggle corpus of Bangladeshi news (~713k articles,
~96% Bengali by character ratio). Labels are **silver, not human-annotated**: a teacher LLM
produced structured event annotations, which were distilled into these small models. No
manual annotation was performed at any stage.

This matters for how you read the metrics: they measure **agreement with LLM-generated
labels**, not with human ground truth. There is no human-labelled evaluation set.

## Limitations & bias

- **Silver labels cap the ceiling.** Systematic teacher-LLM errors are inherited.
- **Domain-specific.** Tuned to Bangladeshi public-safety news; expect degradation on other
  domains, regions, or registers.
- **Opinion pieces leak through.** Editorials and foreign wire stories are sometimes
  classified as events by the upstream gate/router.
- **Entity noise.** NER tags some generic Bengali nouns (e.g. রাজধানীর "of the capital",
  সদর "HQ") as locations.
- **No calibration.** Confidence-style outputs are uncalibrated; do not read them as
  probabilities of correctness.
- **INT8 quantization** trades a little accuracy for ~4× size reduction and CPU speed.
- **Not for high-stakes use.** Casualty counts and event classifications are unverified
  model output and must not be used for emergency response, journalism, or policy without
  human review.

## License

Released under **cc-by-nc-4.0** — free to share and adapt **for non-commercial purposes**
with attribution. Note that the training corpus consists of copyrighted news articles and
the labels were LLM-distilled; downstream users are responsible for their own compliance.

## Citation

```bibtex
@software{newsintel_ai,
  title  = {NewsIntel AI: distilled multilingual event extraction for Bangladeshi news},
  author = {Md. Sheikh Saidy},
  year   = {2026},
  url    = {https://huggingface.co/saidylive/newsintel-event-type}
}
```