Bridgeai Lab Sem Ncg

---
name: bridgeai-lab-sem-ncg
description: Compute BridgeAI-Lab/Sem-nCG via the HuggingFace `evaluate` library. Use when the user has predictions + references and wants the canonical implementation of BridgeAI-Lab/Sem-nCG.
metadata:
  skill_kind: metric
  source_lib: huggingface-evaluate
  hf_module: BridgeAI-Lab/Sem-nCG
  source: library_introspection
---

# bridgeai-lab-sem-ncg

> Metric `BridgeAI-Lab/Sem-nCG` from the HuggingFace `evaluate` library.

## When to invoke

User asks to compute `BridgeAI-Lab/Sem-nCG` or wants HF evaluate's canonical version.

## Recipe

```python
import evaluate
metric = evaluate.load("BridgeAI-Lab/Sem-nCG")
result = metric.compute(predictions=preds, references=refs)
print(result)
```

## Don'ts

- Don't assume your in-house `BridgeAI-Lab/Sem-nCG` matches HF — version conventions vary.
- Many evaluate metrics have task-specific arguments (`average=`, `lang=`, `model_type=`); read the metric card before reporting numbers.