> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/curator/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/curator/_mcp/server.

# nemo_curator.stages.text.experimental.translation.evaluation.text_quality

Translation quality metrics for translated and backtranslated text.

## Module Contents

### Classes

| Name                                                                                                                          | Description                                               |
| ----------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------- |
| [`TextQualityMetricStage`](#nemo_curator-stages-text-experimental-translation-evaluation-text_quality-TextQualityMetricStage) | Compute translation quality metrics for two text columns. |

### Functions

| Name                                                                                                                                    | Description                                                    |
| --------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------- |
| [`compute_text_quality_metric`](#nemo_curator-stages-text-experimental-translation-evaluation-text_quality-compute_text_quality_metric) | Compute one translation quality metric and its pass/fail flag. |

### API

```python
class nemo_curator.stages.text.experimental.translation.evaluation.text_quality.TextQualityMetricStage(
    name: str = 'TextQualityMetricStage',
    reference_text_field: str = 'text',
    hypothesis_text_field: str = 'backtranslated_text',
    metrics: list[dict[str, typing.Any]] = list(),
    filter_enabled: bool = False,
    pass_column: str = 'is_quality_metric_passed'
)
```

Dataclass

**Bases:** [ProcessingStage\[DocumentBatch, DocumentBatch\]](/nemo-curator/nemo_curator/stages/base#nemo_curator-stages-base-ProcessingStage)

Compute translation quality metrics for two text columns.

**`filter_enabled`** `bool = False`

---

**`hypothesis_text_field`** `str = 'backtranslated_text'`

---

**`metrics`** `list[dict[str, Any]] = field(default_factory=list)`

---

**`name`** `str = 'TextQualityMetricStage'`

---

**`pass_column`** `str = 'is_quality_metric_passed'`

---

**`reference_text_field`** `str = 'text'`

---

```python
nemo_curator.stages.text.experimental.translation.evaluation.text_quality.TextQualityMetricStage.inputs() -> tuple[list[str], list[str]]
```

```python
nemo_curator.stages.text.experimental.translation.evaluation.text_quality.TextQualityMetricStage.outputs() -> tuple[list[str], list[str]]
```

```python
nemo_curator.stages.text.experimental.translation.evaluation.text_quality.TextQualityMetricStage.process(
    batch: nemo_curator.tasks.DocumentBatch
) -> nemo_curator.tasks.DocumentBatch
```

```python
nemo_curator.stages.text.experimental.translation.evaluation.text_quality.compute_text_quality_metric(
    hypothesis: str,
    reference: str,
    metric_type: str,
    threshold: float
) -> tuple[float, bool]
```

Compute one translation quality metric and its pass/fail flag.