explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-10-02 09:56:39 +03:00
Code Issues Packages Projects Releases Wiki Activity

Explain architectures better in docs

Browse Source
This commit is contained in:
Matthew Honnibal 2019-03-23 16:18:36 +01:00
parent 350785d8ce
commit 475c3c3b15
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
website/docs/api/textcategorizer.md
View File

@ -58,8 +58,9 @@ argument.
| Name | Description |
| -------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `"ensemble"` | **Default:** Stacked ensemble of a unigram bag-of-words model and a neural network model. The neural network uses a CNN with mean pooling and attention. |
| `"simple_cnn"` | A neural network model where token vectors are calculated using a CNN. The vectors are mean pooled and used as features in a feed-forward network. |
| `"ensemble"` | **Default:** Stacked ensemble of a bag-of-words model and a neural network model. The neural network uses a CNN with mean pooling and attention. The "ngram_size" and "attr" arguments can be used to configure the feature extraction for the bag-of-words model.
| `"simple_cnn"` | A neural network model where token vectors are calculated using a CNN. The vectors are mean pooled and used as features in a feed-forward network. This architecture is usually less accurate than the ensemble, but runs faster. |
| `"bow"` | An ngram "bag-of-words" model. This architecture should run much faster than the others, but may not be as accurate, especially if texts are short. The features extracted can be controlled using the keyword arguments ngram_size and attr. For instance, `ngram_size=3` and `attr="lower"` would give lower-cased unigram, trigram and bigram features. 2, 3 or 4 are usually good choices of ngram size. |
## TextCategorizer.\_\_call\_\_ {#call tag="method"}