explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-07-15 02:32:37 +03:00
Code Issues Packages Projects Releases Wiki Activity

Run prettier on spancategorizer.mdx

Browse Source
This commit is contained in:
Lj Miranda 2023-01-17 10:20:57 +08:00
parent e61f0a4035
commit 02ffe45770
1 changed files with 16 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
website/docs/api/spancategorizer.mdx
View File

@ -17,8 +17,8 @@ This component comes in two forms: `spancat` and `spancat_exclusive`. When you
need to perform multi-label classification on your spans, use `spancat`. The need to perform multi-label classification on your spans, use `spancat`. The
`spancat` component uses a `Logistic` layer where the output class probabilities `spancat` component uses a `Logistic` layer where the output class probabilities
are independent for each class. However, if you need to predict exactly one true are independent for each class. However, if you need to predict exactly one true
class for a span, then use `spancat_exclusive`. It uses a `Softmax` layer and treats class for a span, then use `spancat_exclusive`. It uses a `Softmax` layer and
the entities as a multi-class problem. treats the entities as a multi-class problem.
Predicted spans will be saved in a [`SpanGroup`](/api/spangroup) on the doc. Predicted spans will be saved in a [`SpanGroup`](/api/spangroup) on the doc.
Individual span scores can be found in `spangroup.attrs["scores"]`. Individual span scores can be found in `spangroup.attrs["scores"]`.
@ -59,7 +59,6 @@ architectures and their arguments and hyperparameters.
> nlp.add_pipe("spancat", config=config) > nlp.add_pipe("spancat", config=config)
> ``` > ```
> #### Example (spancat_exclusive) > #### Example (spancat_exclusive)
> >
> ```python > ```python
@ -76,9 +75,8 @@ architectures and their arguments and hyperparameters.
> nlp.add_pipe("spancat_exclusive", config=config) > nlp.add_pipe("spancat_exclusive", config=config)
> ``` > ```
| Setting | Description | | Setting | Description |
| -------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | ----------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `suggester` | A function that [suggests spans](#suggesters). Spans are returned as a ragged array with two integer columns, for the start and end positions. Defaults to [`ngram_suggester`](#ngram_suggester). ~~Callable[[Iterable[Doc], Optional[Ops]], Ragged]~~ | | `suggester` | A function that [suggests spans](#suggesters). Spans are returned as a ragged array with two integer columns, for the start and end positions. Defaults to [`ngram_suggester`](#ngram_suggester). ~~Callable[[Iterable[Doc], Optional[Ops]], Ragged]~~ |
| `model` | A model instance that is given a a list of documents and `(start, end)` indices representing candidate span offsets. The model predicts a probability for each category for each span. Defaults to [SpanCategorizer](/api/architectures#SpanCategorizer). ~~Model[Tuple[List[Doc], Ragged], Floats2d]~~ | | `model` | A model instance that is given a a list of documents and `(start, end)` indices representing candidate span offsets. The model predicts a probability for each category for each span. Defaults to [SpanCategorizer](/api/architectures#SpanCategorizer). ~~Model[Tuple[List[Doc], Ragged], Floats2d]~~ |
| `spans_key` | Key of the [`Doc.spans`](/api/doc#spans) dict to save the spans under. During initialization and training, the component will look for spans on the reference document under the same key. Defaults to `"sc"`. ~~str~~ | | `spans_key` | Key of the [`Doc.spans`](/api/doc#spans) dict to save the spans under. During initialization and training, the component will look for spans on the reference document under the same key. Defaults to `"sc"`. ~~str~~ |
@ -88,8 +86,6 @@ architectures and their arguments and hyperparameters.
| `negative_weight` | Multiplier for the loss terms. It can be used to downweight the negative samples if there are too many. It is only available for the `spancat_exclusive` component. Defaults to `1.0`. ~~float~~ | | `negative_weight` | Multiplier for the loss terms. It can be used to downweight the negative samples if there are too many. It is only available for the `spancat_exclusive` component. Defaults to `1.0`. ~~float~~ |
| `allow_overlap` | If `True`, the data is assumed to contain overlapping spans. It is only available for the `spancat_exclusive` component. Defaults to `True`. ~~bool~~ | | `allow_overlap` | If `True`, the data is assumed to contain overlapping spans. It is only available for the `spancat_exclusive` component. Defaults to `True`. ~~bool~~ |
```python ```python
%%GITHUB_SPACY/spacy/pipeline/spancat.py %%GITHUB_SPACY/spacy/pipeline/spancat.py
``` ```