explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-06-02 04:03:19 +03:00
Code Issues Packages Projects Releases Wiki Activity

Update docs [ci skip]

Browse Source
This commit is contained in:
Ines Montani 2020-08-20 16:17:25 +02:00
parent 7f2e4244df
commit 04e4d59235
4 changed files with 10 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.gitignore vendored
View File

@ -18,8 +18,6 @@ website/.npm
website/logs website/logs
*.log *.log
npm-debug.log* npm-debug.log*
website/www/
website/_deploy.sh
quickstart-training-generator.js quickstart-training-generator.js
# Cython / C extensions # Cython / C extensions

6
website/docs/api/architectures.md
View File

@ -399,7 +399,7 @@ one component.
> subword_features = true > subword_features = true
> ``` > ```
Build a transition-based parser model. Can apply to NER or dependency-parsing. Build a transition-based parser model. Can apply to NER or dependency parsing.
Transition-based parsing is an approach to structured prediction where the task Transition-based parsing is an approach to structured prediction where the task
of predicting the structure is mapped to a series of state transitions. You of predicting the structure is mapped to a series of state transitions. You
might find [this tutorial](https://explosion.ai/blog/parsing-english-in-python) might find [this tutorial](https://explosion.ai/blog/parsing-english-in-python)
@ -416,8 +416,6 @@ consists of either two or three subnetworks:
state representation. If not present, the output from the lower model is used state representation. If not present, the output from the lower model is used
as action scores directly. as action scores directly.
<!-- TODO: model return type -->
| Name | Description | | Name | Description |
| ------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | ------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `tok2vec` | Subnetwork to map tokens into vector representations. ~~Model[List[Doc], List[Floats2d]]~~ | | `tok2vec` | Subnetwork to map tokens into vector representations. ~~Model[List[Doc], List[Floats2d]]~~ |
@ -426,7 +424,7 @@ consists of either two or three subnetworks:
| `maxout_pieces` | How many pieces to use in the state prediction layer. Recommended values are `1`, `2` or `3`. If `1`, the maxout non-linearity is replaced with a [`Relu`](https://thinc.ai/docs/api-layers#relu) non-linearity if `use_upper` is `True`, and no non-linearity if `False`. ~~int~~ | | `maxout_pieces` | How many pieces to use in the state prediction layer. Recommended values are `1`, `2` or `3`. If `1`, the maxout non-linearity is replaced with a [`Relu`](https://thinc.ai/docs/api-layers#relu) non-linearity if `use_upper` is `True`, and no non-linearity if `False`. ~~int~~ |
| `use_upper` | Whether to use an additional hidden layer after the state vector in order to predict the action scores. It is recommended to set this to `False` for large pretrained models such as transformers, and `True` for smaller networks. The upper layer is computed on CPU, which becomes a bottleneck on larger GPU-based models, where it's also less necessary. ~~bool~~ | | `use_upper` | Whether to use an additional hidden layer after the state vector in order to predict the action scores. It is recommended to set this to `False` for large pretrained models such as transformers, and `True` for smaller networks. The upper layer is computed on CPU, which becomes a bottleneck on larger GPU-based models, where it's also less necessary. ~~bool~~ |
| `nO` | The number of actions the model will predict between. Usually inferred from data at the beginning of training, or loaded from disk. ~~int~~ | | `nO` | The number of actions the model will predict between. Usually inferred from data at the beginning of training, or loaded from disk. ~~int~~ |
| **CREATES** | The model using the architecture. ~~Model~~ | | **CREATES** | The model using the architecture. ~~Model[List[Docs], List[List[Floats2d]]]~~ |
### spacy.BILUOTagger.v1 {#BILUOTagger source="spacy/ml/models/simple_ner.py"} ### spacy.BILUOTagger.v1 {#BILUOTagger source="spacy/ml/models/simple_ner.py"}

10
website/docs/usage/training.md
View File

@ -404,11 +404,15 @@ recipe once the dish has already been prepared. You have to make a new one.
spaCy includes a variety of built-in [architectures](/api/architectures) for spaCy includes a variety of built-in [architectures](/api/architectures) for
different tasks. For example: different tasks. For example:
<!-- TODO: select example architectures to showcase --> <!-- TODO: model return types -->
| Architecture | Description | | Architecture | Description |
| ----------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | ----------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| [HashEmbedCNN](/api/architectures#HashEmbedCNN) | Build spaCy’s “standard” embedding layer, which uses hash embedding with subword features and a CNN with layer-normalized maxout. ~~Model[List[Doc], List[Floats2d]]~~ | | [HashEmbedCNN](/api/architectures#HashEmbedCNN) | Build spaCy’s "standard" embedding layer, which uses hash embedding with subword features and a CNN with layer-normalized maxout. ~~Model[List[Doc], List[Floats2d]]~~ |
| [TransitionBasedParser](/api/architectures#TransitionBasedParser) | Build a [transition-based parser](https://explosion.ai/blog/parsing-english-in-python) model used in the default [`EntityRecognizer`](/api/entityrecognizer) and [`DependencyParser`](/api/dependencyparser). ~~Model[List[Docs], List[List[Floats2d]]]~~ |
| [TextCatEnsemble](/api/architectures#TextCatEnsemble) | Stacked ensemble of a bag-of-words model and a neural network model with an internal CNN embedding layer. Used in the default [`TextCategorizer`](/api/textcategorizer). ~~Model~~ |
<!-- TODO: link to not yet existing usage page on custom architectures etc. -->
### Metrics, training output and weighted scores {#metrics} ### Metrics, training output and weighted scores {#metrics}

12
website/src/widgets/quickstart-training-generator.js
View File

File diff suppressed because one or more lines are too long